stories15M_MOE / model.safetensors.index.json
ngxson's picture
ngxson HF staff
model.safetensors.index.json
04b43ee
{
"metadata": {
"total_size": 72744704,
"format": "safetensors"
},
"weight_map": {
"model.embed_tokens.weight": "model.safetensors",
"model.norm.weight": "model.safetensors",
"lm_head.weight": "model.safetensors",
"model.layers.0.input_layernorm.weight": "model.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.gate.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
"model.layers.0.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
"model.layers.1.input_layernorm.weight": "model.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.gate.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
"model.layers.1.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
"model.layers.2.input_layernorm.weight": "model.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.gate.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
"model.layers.2.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
"model.layers.3.input_layernorm.weight": "model.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.gate.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
"model.layers.3.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
"model.layers.4.input_layernorm.weight": "model.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.gate.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
"model.layers.4.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
"model.layers.5.input_layernorm.weight": "model.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.gate.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
"model.layers.5.block_sparse_moe.experts.3.w3.weight": "model.safetensors"
}
}