| --- |
| license: apache-2.0 |
| pipeline_tag: question-answering |
| library_name: transformers |
| --- |
| |
| # File information |
|
|
| The repository contains the following file information: |
|
|
| Filename: tokenizer.json |
| Content: "Content of the file is larger than 50 KB, too long to display." |
|
|
| Filename: model.safetensors.index.json |
| Content: { |
| "metadata": { |
| "total_size": 7108352000 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00002-of-00002.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", |
| "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", |
| "model.layers.23.mlp |
