hf-moshiko / model.safetensors.index.json
ylacombe's picture
ylacombe HF staff
Upload MoshiForConditionalGeneration
0fc9030 verified
raw
history blame
69.7 kB
{
"metadata": {
"total_size": 15567761090
},
"weight_map": {
"audio_encoder.decoder.layers.0.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.0.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.11.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.11.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.12.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.12.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.12.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.12.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.14.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.14.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.2.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.2.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.3.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.3.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.3.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.3.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.5.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.5.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.6.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.6.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.6.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.6.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.8.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.8.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.9.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.9.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.9.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder.layers.9.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.0.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.1.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.2.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.3.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.4.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.5.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.6.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.decoder_transformer.layers.7.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.downsample.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.0.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.0.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.1.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.1.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.1.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.1.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.10.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.10.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.10.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.10.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.12.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.12.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.14.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.14.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.4.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.4.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.4.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.4.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.6.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.6.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.7.block.1.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.7.block.1.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.7.block.3.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.7.block.3.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.9.conv.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder.layers.9.conv.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.0.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.1.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.2.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.3.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.4.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.5.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.6.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.mlp_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.encoder_transformer.layers.7.self_attn_layer_scale.scale": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.input_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.0.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.1.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.10.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.11.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.12.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.13.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.14.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.15.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.16.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.17.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.18.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.19.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.2.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.20.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.21.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.22.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.23.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.24.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.25.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.26.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.27.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.28.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.29.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.3.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.30.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.4.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.5.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.6.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.7.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.8.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.layers.9.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.acoustic_residual_vector_quantizer.output_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.semantic_residual_vector_quantizer.input_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.cluster_usage": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.embed_sum": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.semantic_residual_vector_quantizer.layers.0.codebook.initialized": "model-00001-of-00004.safetensors",
"audio_encoder.quantizer.semantic_residual_vector_quantizer.output_proj.weight": "model-00001-of-00004.safetensors",
"audio_encoder.upsample.conv.weight": "model-00001-of-00004.safetensors",
"decoder.lm_head.weight": "model-00003-of-00004.safetensors",
"decoder.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.0.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.1.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.10.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.10.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.10.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.10.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.10.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.10.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.11.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.12.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.13.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.14.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.15.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.16.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.17.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.18.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.19.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.2.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.20.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.mlp.fc1.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.mlp.fc2.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.21.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.22.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.22.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.22.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.22.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
"decoder.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.23.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.24.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.25.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.26.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.27.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.28.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.29.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.3.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.30.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.31.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.4.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.5.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.6.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.7.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.8.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.layers.9.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
"decoder.model.norm.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.0.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.1.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.2.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.3.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.4.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.5.weight": "model-00003-of-00004.safetensors",
"depth_decoder.embed_tokens.6.weight": "model-00003-of-00004.safetensors",
"depth_decoder.input_projections.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.0.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.1.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.2.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.2.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.2.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.2.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
"depth_decoder.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.3.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.4.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.layers.5.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
"depth_decoder.lm_heads.weight": "model-00004-of-00004.safetensors",
"depth_decoder.text_embed_tokens.weight": "model-00003-of-00004.safetensors",
"embed_tokens.0.weight": "model-00001-of-00004.safetensors",
"embed_tokens.1.weight": "model-00001-of-00004.safetensors",
"embed_tokens.10.weight": "model-00001-of-00004.safetensors",
"embed_tokens.11.weight": "model-00001-of-00004.safetensors",
"embed_tokens.12.weight": "model-00001-of-00004.safetensors",
"embed_tokens.13.weight": "model-00001-of-00004.safetensors",
"embed_tokens.14.weight": "model-00001-of-00004.safetensors",
"embed_tokens.15.weight": "model-00001-of-00004.safetensors",
"embed_tokens.2.weight": "model-00001-of-00004.safetensors",
"embed_tokens.3.weight": "model-00001-of-00004.safetensors",
"embed_tokens.4.weight": "model-00001-of-00004.safetensors",
"embed_tokens.5.weight": "model-00001-of-00004.safetensors",
"embed_tokens.6.weight": "model-00001-of-00004.safetensors",
"embed_tokens.7.weight": "model-00001-of-00004.safetensors",
"embed_tokens.8.weight": "model-00001-of-00004.safetensors",
"embed_tokens.9.weight": "model-00001-of-00004.safetensors"
}
}