Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_channel_1_virology_Complete Random
file_name: llama_channel_1_virology_Complete Random_5000_5.pt
pruning_style: channel
community: 1
pruning_ratio: 20
dataset_label: virology
sparsity_ratio: 20
['tasksource/mmlu', 'virology']
finetune: Complete Random
modules_size: 42
modules: ['14_mlp.down', '12_gate', '12_attn.v', '24_attn.q', '22_attn.k', '4_attn.o', '8_gate', '12_attn.q', '19_mlp.up', '26_gate', '9_attn.k', '17_attn.v', '17_gate', '5_mlp.down', '8_attn.o', '11_attn.k', '22_attn.v', '17_attn.q', '16_attn.k', '25_attn.o', '3_attn.o', '15_attn.v', '16_attn.q', '13_mlp.up', '20_attn.q', '18_attn.q', '29_attn.k', '21_attn.o', '27_mlp.down', '29_attn.o', '11_attn.v', '30_attn.q', '20_attn.o', '3_attn.q', '24_attn.v', '8_attn.k', '21_attn.v', '13_attn.o', '4_mlp.up', '11_mlp.down', '5_gate', '22_mlp.down']
rank: 1
tags: ['model: llama', 'repo_name: llama_channel_1_virology_Complete Random', 'file_name: llama_channel_1_virology_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: channel', 'community: 1', 'pruning_ratio: 20', 'dataset_label: virology', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'virology']", 'finetune: Complete Random', 'modules_size: 42', "modules: ['14_mlp.down', '12_gate', '12_attn.v', '24_attn.q', '22_attn.k', '4_attn.o', '8_gate', '12_attn.q', '19_mlp.up', '26_gate', '9_attn.k', '17_attn.v', '17_gate', '5_mlp.down', '8_attn.o', '11_attn.k', '22_attn.v', '17_attn.q', '16_attn.k', '25_attn.o', '3_attn.o', '15_attn.v', '16_attn.q', '13_mlp.up', '20_attn.q', '18_attn.q', '29_attn.k', '21_attn.o', '27_mlp.down', '29_attn.o', '11_attn.v', '30_attn.q', '20_attn.o', '3_attn.q', '24_attn.v', '8_attn.k', '21_attn.v', '13_attn.o', '4_mlp.up', '11_mlp.down', '5_gate', '22_mlp.down']", 'rank: 1']
text-generation-inference
| { | |
| "metadata": { | |
| "total_size": 26953662464 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00006-of-00006.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.norm.weight": "model-00006-of-00006.safetensors" | |
| } | |
| } | |