|
{ |
|
"metadata": { |
|
"total_size": 6387534934 |
|
}, |
|
"weight_map": { |
|
"h.0.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.0.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.0.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.1.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.1.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.1.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.10.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.10.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.10.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.11.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.11.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.11.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.12.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.12.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.12.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.13.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.13.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.13.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.14.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.14.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.14.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.15.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.15.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.15.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.16.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.16.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.16.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.17.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.17.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.17.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.18.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.18.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.18.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.19.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.19.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.19.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.2.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.2.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.2.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.20.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.20.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.20.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.21.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.21.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.21.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.22.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.22.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.22.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.23.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.23.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.23.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.24.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.24.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.24.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.25.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.25.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.25.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.26.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.26.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.26.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.27.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.27.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.27.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.28.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.28.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.28.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.29.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.29.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.29.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.3.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.3.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.3.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.30.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.30.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.30.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.31.input_layernorm.bias": "model-00002-of-00002.safetensors", |
|
"h.31.input_layernorm.weight": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_4h_to_h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_h_to_4h.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.dense.weight": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.dense.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.dense.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.query_key_value.weight.nested_absmax": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.query_key_value.weight.nested_quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors", |
|
"h.31.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors", |
|
"h.4.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.4.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.4.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.5.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.5.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.5.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.6.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.6.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.6.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.7.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.7.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.7.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.8.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.8.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.8.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.9.input_layernorm.bias": "model-00001-of-00002.safetensors", |
|
"h.9.input_layernorm.weight": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_4h_to_h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_4h_to_h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_h_to_4h.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_h_to_4h.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.dense.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.dense.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.dense.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.query_key_value.weight.nested_absmax": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.query_key_value.weight.nested_quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors", |
|
"h.9.self_attention.query_key_value.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", |
|
"ln_f.bias": "model-00002-of-00002.safetensors", |
|
"ln_f.weight": "model-00002-of-00002.safetensors", |
|
"word_embeddings.weight": "model-00001-of-00002.safetensors" |
|
} |
|
} |
|
|