{ "metadata": { "total_size": 2023563264 }, "weight_map": { "model.embed_in.weight": "model.safetensors", "model.embed_out.weight": "model.safetensors", "model.final_layer_norm.bias": "model.safetensors", "model.final_layer_norm.weight": "model.safetensors", "model.h.0.attention.dense.bias": "model.safetensors", "model.h.0.attention.dense.weight": "model.safetensors", "model.h.0.attention.query_key_value.bias": "model.safetensors", "model.h.0.attention.query_key_value.weight": "model.safetensors", "model.h.0.input_layernorm.bias": "model.safetensors", "model.h.0.input_layernorm.weight": "model.safetensors", "model.h.0.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.0.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.0.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.0.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.0.post_attention_layernorm.bias": "model.safetensors", "model.h.0.post_attention_layernorm.weight": "model.safetensors", "model.h.1.attention.dense.bias": "model.safetensors", "model.h.1.attention.dense.weight": "model.safetensors", "model.h.1.attention.query_key_value.bias": "model.safetensors", "model.h.1.attention.query_key_value.weight": "model.safetensors", "model.h.1.input_layernorm.bias": "model.safetensors", "model.h.1.input_layernorm.weight": "model.safetensors", "model.h.1.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.1.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.1.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.1.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.1.post_attention_layernorm.bias": "model.safetensors", "model.h.1.post_attention_layernorm.weight": "model.safetensors", "model.h.10.attention.dense.bias": "model.safetensors", "model.h.10.attention.dense.weight": "model.safetensors", "model.h.10.attention.query_key_value.bias": "model.safetensors", "model.h.10.attention.query_key_value.weight": "model.safetensors", "model.h.10.input_layernorm.bias": "model.safetensors", "model.h.10.input_layernorm.weight": "model.safetensors", "model.h.10.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.10.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.10.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.10.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.10.post_attention_layernorm.bias": "model.safetensors", "model.h.10.post_attention_layernorm.weight": "model.safetensors", "model.h.11.attention.dense.bias": "model.safetensors", "model.h.11.attention.dense.weight": "model.safetensors", "model.h.11.attention.query_key_value.bias": "model.safetensors", "model.h.11.attention.query_key_value.weight": "model.safetensors", "model.h.11.input_layernorm.bias": "model.safetensors", "model.h.11.input_layernorm.weight": "model.safetensors", "model.h.11.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.11.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.11.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.11.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.11.post_attention_layernorm.bias": "model.safetensors", "model.h.11.post_attention_layernorm.weight": "model.safetensors", "model.h.12.attention.dense.bias": "model.safetensors", "model.h.12.attention.dense.weight": "model.safetensors", "model.h.12.attention.query_key_value.bias": "model.safetensors", "model.h.12.attention.query_key_value.weight": "model.safetensors", "model.h.12.input_layernorm.bias": "model.safetensors", "model.h.12.input_layernorm.weight": "model.safetensors", "model.h.12.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.12.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.12.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.12.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.12.post_attention_layernorm.bias": "model.safetensors", "model.h.12.post_attention_layernorm.weight": "model.safetensors", "model.h.13.attention.dense.bias": "model.safetensors", "model.h.13.attention.dense.weight": "model.safetensors", "model.h.13.attention.query_key_value.bias": "model.safetensors", "model.h.13.attention.query_key_value.weight": "model.safetensors", "model.h.13.input_layernorm.bias": "model.safetensors", "model.h.13.input_layernorm.weight": "model.safetensors", "model.h.13.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.13.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.13.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.13.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.13.post_attention_layernorm.bias": "model.safetensors", "model.h.13.post_attention_layernorm.weight": "model.safetensors", "model.h.14.attention.dense.bias": "model.safetensors", "model.h.14.attention.dense.weight": "model.safetensors", "model.h.14.attention.query_key_value.bias": "model.safetensors", "model.h.14.attention.query_key_value.weight": "model.safetensors", "model.h.14.input_layernorm.bias": "model.safetensors", "model.h.14.input_layernorm.weight": "model.safetensors", "model.h.14.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.14.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.14.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.14.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.14.post_attention_layernorm.bias": "model.safetensors", "model.h.14.post_attention_layernorm.weight": "model.safetensors", "model.h.15.attention.dense.bias": "model.safetensors", "model.h.15.attention.dense.weight": "model.safetensors", "model.h.15.attention.query_key_value.bias": "model.safetensors", "model.h.15.attention.query_key_value.weight": "model.safetensors", "model.h.15.input_layernorm.bias": "model.safetensors", "model.h.15.input_layernorm.weight": "model.safetensors", "model.h.15.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.15.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.15.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.15.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.15.post_attention_layernorm.bias": "model.safetensors", "model.h.15.post_attention_layernorm.weight": "model.safetensors", "model.h.2.attention.dense.bias": "model.safetensors", "model.h.2.attention.dense.weight": "model.safetensors", "model.h.2.attention.query_key_value.bias": "model.safetensors", "model.h.2.attention.query_key_value.weight": "model.safetensors", "model.h.2.input_layernorm.bias": "model.safetensors", "model.h.2.input_layernorm.weight": "model.safetensors", "model.h.2.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.2.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.2.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.2.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.2.post_attention_layernorm.bias": "model.safetensors", "model.h.2.post_attention_layernorm.weight": "model.safetensors", "model.h.3.attention.dense.bias": "model.safetensors", "model.h.3.attention.dense.weight": "model.safetensors", "model.h.3.attention.query_key_value.bias": "model.safetensors", "model.h.3.attention.query_key_value.weight": "model.safetensors", "model.h.3.input_layernorm.bias": "model.safetensors", "model.h.3.input_layernorm.weight": "model.safetensors", "model.h.3.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.3.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.3.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.3.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.3.post_attention_layernorm.bias": "model.safetensors", "model.h.3.post_attention_layernorm.weight": "model.safetensors", "model.h.4.attention.dense.bias": "model.safetensors", "model.h.4.attention.dense.weight": "model.safetensors", "model.h.4.attention.query_key_value.bias": "model.safetensors", "model.h.4.attention.query_key_value.weight": "model.safetensors", "model.h.4.input_layernorm.bias": "model.safetensors", "model.h.4.input_layernorm.weight": "model.safetensors", "model.h.4.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.4.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.4.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.4.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.4.post_attention_layernorm.bias": "model.safetensors", "model.h.4.post_attention_layernorm.weight": "model.safetensors", "model.h.5.attention.dense.bias": "model.safetensors", "model.h.5.attention.dense.weight": "model.safetensors", "model.h.5.attention.query_key_value.bias": "model.safetensors", "model.h.5.attention.query_key_value.weight": "model.safetensors", "model.h.5.input_layernorm.bias": "model.safetensors", "model.h.5.input_layernorm.weight": "model.safetensors", "model.h.5.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.5.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.5.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.5.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.5.post_attention_layernorm.bias": "model.safetensors", "model.h.5.post_attention_layernorm.weight": "model.safetensors", "model.h.6.attention.dense.bias": "model.safetensors", "model.h.6.attention.dense.weight": "model.safetensors", "model.h.6.attention.query_key_value.bias": "model.safetensors", "model.h.6.attention.query_key_value.weight": "model.safetensors", "model.h.6.input_layernorm.bias": "model.safetensors", "model.h.6.input_layernorm.weight": "model.safetensors", "model.h.6.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.6.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.6.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.6.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.6.post_attention_layernorm.bias": "model.safetensors", "model.h.6.post_attention_layernorm.weight": "model.safetensors", "model.h.7.attention.dense.bias": "model.safetensors", "model.h.7.attention.dense.weight": "model.safetensors", "model.h.7.attention.query_key_value.bias": "model.safetensors", "model.h.7.attention.query_key_value.weight": "model.safetensors", "model.h.7.input_layernorm.bias": "model.safetensors", "model.h.7.input_layernorm.weight": "model.safetensors", "model.h.7.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.7.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.7.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.7.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.7.post_attention_layernorm.bias": "model.safetensors", "model.h.7.post_attention_layernorm.weight": "model.safetensors", "model.h.8.attention.dense.bias": "model.safetensors", "model.h.8.attention.dense.weight": "model.safetensors", "model.h.8.attention.query_key_value.bias": "model.safetensors", "model.h.8.attention.query_key_value.weight": "model.safetensors", "model.h.8.input_layernorm.bias": "model.safetensors", "model.h.8.input_layernorm.weight": "model.safetensors", "model.h.8.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.8.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.8.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.8.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.8.post_attention_layernorm.bias": "model.safetensors", "model.h.8.post_attention_layernorm.weight": "model.safetensors", "model.h.9.attention.dense.bias": "model.safetensors", "model.h.9.attention.dense.weight": "model.safetensors", "model.h.9.attention.query_key_value.bias": "model.safetensors", "model.h.9.attention.query_key_value.weight": "model.safetensors", "model.h.9.input_layernorm.bias": "model.safetensors", "model.h.9.input_layernorm.weight": "model.safetensors", "model.h.9.mlp.dense_4h_to_h.bias": "model.safetensors", "model.h.9.mlp.dense_4h_to_h.weight": "model.safetensors", "model.h.9.mlp.dense_h_to_4h.bias": "model.safetensors", "model.h.9.mlp.dense_h_to_4h.weight": "model.safetensors", "model.h.9.post_attention_layernorm.bias": "model.safetensors", "model.h.9.post_attention_layernorm.weight": "model.safetensors" } }