|
{ |
|
"metadata": { |
|
"total_size": 18604670976 |
|
}, |
|
"weight_map": { |
|
"lm_head.weight": "model-00004-of-00004.safetensors", |
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.14.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.15.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.2.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.20.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.3.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.30.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.ln1.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.ln2.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.32.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.g_idx": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", |
|
"model.layers.33.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.4.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.40.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.48.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.ln1.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.ln2.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.down_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.down_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.down_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.gate_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.up_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.up_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.mlp.up_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.o_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.o_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.q_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.v_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.49.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.5.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.50.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.50.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", |
|
"model.layers.50.self_attn.k_proj.g_idx": "model-00003-of-00004.safetensors", |
|
"model.layers.50.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", |
|
"model.layers.50.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", |
|
"model.layers.50.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", |
|
"model.layers.50.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.50.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.51.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.52.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.53.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.54.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.55.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.56.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.57.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.58.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.ln1.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.ln2.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.down_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.down_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.down_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.gate_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.up_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.up_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.mlp.up_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.k_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.o_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.o_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.q_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.v_proj.g_idx": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", |
|
"model.layers.59.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", |
|
"model.layers.6.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.ln1.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.ln2.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", |
|
"model.norm.weight": "model-00004-of-00004.safetensors" |
|
} |
|
} |
|
|