Commit
•
9c9840a
1
Parent(s):
9a2661d
Upload folder using huggingface_hub
Browse files- config.json +24 -0
- eval_arc.json +25 -0
- eval_hellaswag.json +25 -0
- eval_mmlu.json +417 -0
- eval_truthfulqa.json +25 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +31 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "workdir_7b/ckpt_346",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"max_sequence_length": 2048,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.30.2",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32000
|
| 24 |
+
}
|
eval_arc.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"arc_challenge": {
|
| 4 |
+
"acc": 0.39761092150170646,
|
| 5 |
+
"acc_stderr": 0.01430175222327953,
|
| 6 |
+
"acc_norm": 0.41723549488054607,
|
| 7 |
+
"acc_norm_stderr": 0.014409825518403082
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
"versions": {
|
| 11 |
+
"arc_challenge": 0
|
| 12 |
+
},
|
| 13 |
+
"config": {
|
| 14 |
+
"model": "hf-causal",
|
| 15 |
+
"model_args": "pretrained=workdir_7b/ckpt_349",
|
| 16 |
+
"num_fewshot": 25,
|
| 17 |
+
"batch_size": "16",
|
| 18 |
+
"batch_sizes": [],
|
| 19 |
+
"device": null,
|
| 20 |
+
"no_cache": true,
|
| 21 |
+
"limit": null,
|
| 22 |
+
"bootstrap_iters": 100000,
|
| 23 |
+
"description_dict": {}
|
| 24 |
+
}
|
| 25 |
+
}
|
eval_hellaswag.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"hellaswag": {
|
| 4 |
+
"acc": 0.5480979884485162,
|
| 5 |
+
"acc_stderr": 0.004966640868083862,
|
| 6 |
+
"acc_norm": 0.7380003983270265,
|
| 7 |
+
"acc_norm_stderr": 0.0043882375575267155
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
"versions": {
|
| 11 |
+
"hellaswag": 0
|
| 12 |
+
},
|
| 13 |
+
"config": {
|
| 14 |
+
"model": "hf-causal",
|
| 15 |
+
"model_args": "pretrained=workdir_7b/ckpt_349",
|
| 16 |
+
"num_fewshot": 10,
|
| 17 |
+
"batch_size": "16",
|
| 18 |
+
"batch_sizes": [],
|
| 19 |
+
"device": null,
|
| 20 |
+
"no_cache": true,
|
| 21 |
+
"limit": null,
|
| 22 |
+
"bootstrap_iters": 100000,
|
| 23 |
+
"description_dict": {}
|
| 24 |
+
}
|
| 25 |
+
}
|
eval_mmlu.json
ADDED
|
@@ -0,0 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"hendrycksTest-abstract_algebra": {
|
| 4 |
+
"acc": 0.26,
|
| 5 |
+
"acc_stderr": 0.044084400227680814,
|
| 6 |
+
"acc_norm": 0.26,
|
| 7 |
+
"acc_norm_stderr": 0.044084400227680814
|
| 8 |
+
},
|
| 9 |
+
"hendrycksTest-anatomy": {
|
| 10 |
+
"acc": 0.23703703703703705,
|
| 11 |
+
"acc_stderr": 0.03673731683969506,
|
| 12 |
+
"acc_norm": 0.23703703703703705,
|
| 13 |
+
"acc_norm_stderr": 0.03673731683969506
|
| 14 |
+
},
|
| 15 |
+
"hendrycksTest-astronomy": {
|
| 16 |
+
"acc": 0.25,
|
| 17 |
+
"acc_stderr": 0.03523807393012047,
|
| 18 |
+
"acc_norm": 0.25,
|
| 19 |
+
"acc_norm_stderr": 0.03523807393012047
|
| 20 |
+
},
|
| 21 |
+
"hendrycksTest-business_ethics": {
|
| 22 |
+
"acc": 0.31,
|
| 23 |
+
"acc_stderr": 0.04648231987117316,
|
| 24 |
+
"acc_norm": 0.31,
|
| 25 |
+
"acc_norm_stderr": 0.04648231987117316
|
| 26 |
+
},
|
| 27 |
+
"hendrycksTest-clinical_knowledge": {
|
| 28 |
+
"acc": 0.22641509433962265,
|
| 29 |
+
"acc_stderr": 0.02575755989310675,
|
| 30 |
+
"acc_norm": 0.22641509433962265,
|
| 31 |
+
"acc_norm_stderr": 0.02575755989310675
|
| 32 |
+
},
|
| 33 |
+
"hendrycksTest-college_biology": {
|
| 34 |
+
"acc": 0.2708333333333333,
|
| 35 |
+
"acc_stderr": 0.037161774375660185,
|
| 36 |
+
"acc_norm": 0.2708333333333333,
|
| 37 |
+
"acc_norm_stderr": 0.037161774375660185
|
| 38 |
+
},
|
| 39 |
+
"hendrycksTest-college_chemistry": {
|
| 40 |
+
"acc": 0.28,
|
| 41 |
+
"acc_stderr": 0.045126085985421276,
|
| 42 |
+
"acc_norm": 0.28,
|
| 43 |
+
"acc_norm_stderr": 0.045126085985421276
|
| 44 |
+
},
|
| 45 |
+
"hendrycksTest-college_computer_science": {
|
| 46 |
+
"acc": 0.42,
|
| 47 |
+
"acc_stderr": 0.04960449637488583,
|
| 48 |
+
"acc_norm": 0.42,
|
| 49 |
+
"acc_norm_stderr": 0.04960449637488583
|
| 50 |
+
},
|
| 51 |
+
"hendrycksTest-college_mathematics": {
|
| 52 |
+
"acc": 0.31,
|
| 53 |
+
"acc_stderr": 0.04648231987117316,
|
| 54 |
+
"acc_norm": 0.31,
|
| 55 |
+
"acc_norm_stderr": 0.04648231987117316
|
| 56 |
+
},
|
| 57 |
+
"hendrycksTest-college_medicine": {
|
| 58 |
+
"acc": 0.2543352601156069,
|
| 59 |
+
"acc_stderr": 0.0332055644308557,
|
| 60 |
+
"acc_norm": 0.2543352601156069,
|
| 61 |
+
"acc_norm_stderr": 0.0332055644308557
|
| 62 |
+
},
|
| 63 |
+
"hendrycksTest-college_physics": {
|
| 64 |
+
"acc": 0.21568627450980393,
|
| 65 |
+
"acc_stderr": 0.04092563958237656,
|
| 66 |
+
"acc_norm": 0.21568627450980393,
|
| 67 |
+
"acc_norm_stderr": 0.04092563958237656
|
| 68 |
+
},
|
| 69 |
+
"hendrycksTest-computer_security": {
|
| 70 |
+
"acc": 0.32,
|
| 71 |
+
"acc_stderr": 0.04688261722621504,
|
| 72 |
+
"acc_norm": 0.32,
|
| 73 |
+
"acc_norm_stderr": 0.04688261722621504
|
| 74 |
+
},
|
| 75 |
+
"hendrycksTest-conceptual_physics": {
|
| 76 |
+
"acc": 0.2978723404255319,
|
| 77 |
+
"acc_stderr": 0.029896145682095462,
|
| 78 |
+
"acc_norm": 0.2978723404255319,
|
| 79 |
+
"acc_norm_stderr": 0.029896145682095462
|
| 80 |
+
},
|
| 81 |
+
"hendrycksTest-econometrics": {
|
| 82 |
+
"acc": 0.2631578947368421,
|
| 83 |
+
"acc_stderr": 0.04142439719489361,
|
| 84 |
+
"acc_norm": 0.2631578947368421,
|
| 85 |
+
"acc_norm_stderr": 0.04142439719489361
|
| 86 |
+
},
|
| 87 |
+
"hendrycksTest-electrical_engineering": {
|
| 88 |
+
"acc": 0.2413793103448276,
|
| 89 |
+
"acc_stderr": 0.03565998174135303,
|
| 90 |
+
"acc_norm": 0.2413793103448276,
|
| 91 |
+
"acc_norm_stderr": 0.03565998174135303
|
| 92 |
+
},
|
| 93 |
+
"hendrycksTest-elementary_mathematics": {
|
| 94 |
+
"acc": 0.2724867724867725,
|
| 95 |
+
"acc_stderr": 0.022930973071633356,
|
| 96 |
+
"acc_norm": 0.2724867724867725,
|
| 97 |
+
"acc_norm_stderr": 0.022930973071633356
|
| 98 |
+
},
|
| 99 |
+
"hendrycksTest-formal_logic": {
|
| 100 |
+
"acc": 0.30952380952380953,
|
| 101 |
+
"acc_stderr": 0.04134913018303316,
|
| 102 |
+
"acc_norm": 0.30952380952380953,
|
| 103 |
+
"acc_norm_stderr": 0.04134913018303316
|
| 104 |
+
},
|
| 105 |
+
"hendrycksTest-global_facts": {
|
| 106 |
+
"acc": 0.28,
|
| 107 |
+
"acc_stderr": 0.045126085985421276,
|
| 108 |
+
"acc_norm": 0.28,
|
| 109 |
+
"acc_norm_stderr": 0.045126085985421276
|
| 110 |
+
},
|
| 111 |
+
"hendrycksTest-high_school_biology": {
|
| 112 |
+
"acc": 0.22258064516129034,
|
| 113 |
+
"acc_stderr": 0.023664216671642528,
|
| 114 |
+
"acc_norm": 0.22258064516129034,
|
| 115 |
+
"acc_norm_stderr": 0.023664216671642528
|
| 116 |
+
},
|
| 117 |
+
"hendrycksTest-high_school_chemistry": {
|
| 118 |
+
"acc": 0.18719211822660098,
|
| 119 |
+
"acc_stderr": 0.027444924966882618,
|
| 120 |
+
"acc_norm": 0.18719211822660098,
|
| 121 |
+
"acc_norm_stderr": 0.027444924966882618
|
| 122 |
+
},
|
| 123 |
+
"hendrycksTest-high_school_computer_science": {
|
| 124 |
+
"acc": 0.25,
|
| 125 |
+
"acc_stderr": 0.04351941398892446,
|
| 126 |
+
"acc_norm": 0.25,
|
| 127 |
+
"acc_norm_stderr": 0.04351941398892446
|
| 128 |
+
},
|
| 129 |
+
"hendrycksTest-high_school_european_history": {
|
| 130 |
+
"acc": 0.296969696969697,
|
| 131 |
+
"acc_stderr": 0.035679697722680474,
|
| 132 |
+
"acc_norm": 0.296969696969697,
|
| 133 |
+
"acc_norm_stderr": 0.035679697722680474
|
| 134 |
+
},
|
| 135 |
+
"hendrycksTest-high_school_geography": {
|
| 136 |
+
"acc": 0.19696969696969696,
|
| 137 |
+
"acc_stderr": 0.028335609732463355,
|
| 138 |
+
"acc_norm": 0.19696969696969696,
|
| 139 |
+
"acc_norm_stderr": 0.028335609732463355
|
| 140 |
+
},
|
| 141 |
+
"hendrycksTest-high_school_government_and_politics": {
|
| 142 |
+
"acc": 0.23316062176165803,
|
| 143 |
+
"acc_stderr": 0.030516111371476008,
|
| 144 |
+
"acc_norm": 0.23316062176165803,
|
| 145 |
+
"acc_norm_stderr": 0.030516111371476008
|
| 146 |
+
},
|
| 147 |
+
"hendrycksTest-high_school_macroeconomics": {
|
| 148 |
+
"acc": 0.21025641025641026,
|
| 149 |
+
"acc_stderr": 0.020660597485026935,
|
| 150 |
+
"acc_norm": 0.21025641025641026,
|
| 151 |
+
"acc_norm_stderr": 0.020660597485026935
|
| 152 |
+
},
|
| 153 |
+
"hendrycksTest-high_school_mathematics": {
|
| 154 |
+
"acc": 0.21851851851851853,
|
| 155 |
+
"acc_stderr": 0.025195752251823786,
|
| 156 |
+
"acc_norm": 0.21851851851851853,
|
| 157 |
+
"acc_norm_stderr": 0.025195752251823786
|
| 158 |
+
},
|
| 159 |
+
"hendrycksTest-high_school_microeconomics": {
|
| 160 |
+
"acc": 0.27310924369747897,
|
| 161 |
+
"acc_stderr": 0.02894200404099817,
|
| 162 |
+
"acc_norm": 0.27310924369747897,
|
| 163 |
+
"acc_norm_stderr": 0.02894200404099817
|
| 164 |
+
},
|
| 165 |
+
"hendrycksTest-high_school_physics": {
|
| 166 |
+
"acc": 0.26490066225165565,
|
| 167 |
+
"acc_stderr": 0.03603038545360384,
|
| 168 |
+
"acc_norm": 0.26490066225165565,
|
| 169 |
+
"acc_norm_stderr": 0.03603038545360384
|
| 170 |
+
},
|
| 171 |
+
"hendrycksTest-high_school_psychology": {
|
| 172 |
+
"acc": 0.23119266055045873,
|
| 173 |
+
"acc_stderr": 0.018075750241633156,
|
| 174 |
+
"acc_norm": 0.23119266055045873,
|
| 175 |
+
"acc_norm_stderr": 0.018075750241633156
|
| 176 |
+
},
|
| 177 |
+
"hendrycksTest-high_school_statistics": {
|
| 178 |
+
"acc": 0.22685185185185186,
|
| 179 |
+
"acc_stderr": 0.028561650102422256,
|
| 180 |
+
"acc_norm": 0.22685185185185186,
|
| 181 |
+
"acc_norm_stderr": 0.028561650102422256
|
| 182 |
+
},
|
| 183 |
+
"hendrycksTest-high_school_us_history": {
|
| 184 |
+
"acc": 0.2696078431372549,
|
| 185 |
+
"acc_stderr": 0.031145570659486782,
|
| 186 |
+
"acc_norm": 0.2696078431372549,
|
| 187 |
+
"acc_norm_stderr": 0.031145570659486782
|
| 188 |
+
},
|
| 189 |
+
"hendrycksTest-high_school_world_history": {
|
| 190 |
+
"acc": 0.28270042194092826,
|
| 191 |
+
"acc_stderr": 0.029312814153955917,
|
| 192 |
+
"acc_norm": 0.28270042194092826,
|
| 193 |
+
"acc_norm_stderr": 0.029312814153955917
|
| 194 |
+
},
|
| 195 |
+
"hendrycksTest-human_aging": {
|
| 196 |
+
"acc": 0.32286995515695066,
|
| 197 |
+
"acc_stderr": 0.03138147637575498,
|
| 198 |
+
"acc_norm": 0.32286995515695066,
|
| 199 |
+
"acc_norm_stderr": 0.03138147637575498
|
| 200 |
+
},
|
| 201 |
+
"hendrycksTest-human_sexuality": {
|
| 202 |
+
"acc": 0.3435114503816794,
|
| 203 |
+
"acc_stderr": 0.041649760719448786,
|
| 204 |
+
"acc_norm": 0.3435114503816794,
|
| 205 |
+
"acc_norm_stderr": 0.041649760719448786
|
| 206 |
+
},
|
| 207 |
+
"hendrycksTest-international_law": {
|
| 208 |
+
"acc": 0.2727272727272727,
|
| 209 |
+
"acc_stderr": 0.04065578140908705,
|
| 210 |
+
"acc_norm": 0.2727272727272727,
|
| 211 |
+
"acc_norm_stderr": 0.04065578140908705
|
| 212 |
+
},
|
| 213 |
+
"hendrycksTest-jurisprudence": {
|
| 214 |
+
"acc": 0.26851851851851855,
|
| 215 |
+
"acc_stderr": 0.04284467968052192,
|
| 216 |
+
"acc_norm": 0.26851851851851855,
|
| 217 |
+
"acc_norm_stderr": 0.04284467968052192
|
| 218 |
+
},
|
| 219 |
+
"hendrycksTest-logical_fallacies": {
|
| 220 |
+
"acc": 0.2147239263803681,
|
| 221 |
+
"acc_stderr": 0.03226219377286774,
|
| 222 |
+
"acc_norm": 0.2147239263803681,
|
| 223 |
+
"acc_norm_stderr": 0.03226219377286774
|
| 224 |
+
},
|
| 225 |
+
"hendrycksTest-machine_learning": {
|
| 226 |
+
"acc": 0.25892857142857145,
|
| 227 |
+
"acc_stderr": 0.04157751539865629,
|
| 228 |
+
"acc_norm": 0.25892857142857145,
|
| 229 |
+
"acc_norm_stderr": 0.04157751539865629
|
| 230 |
+
},
|
| 231 |
+
"hendrycksTest-management": {
|
| 232 |
+
"acc": 0.18446601941747573,
|
| 233 |
+
"acc_stderr": 0.03840423627288276,
|
| 234 |
+
"acc_norm": 0.18446601941747573,
|
| 235 |
+
"acc_norm_stderr": 0.03840423627288276
|
| 236 |
+
},
|
| 237 |
+
"hendrycksTest-marketing": {
|
| 238 |
+
"acc": 0.3076923076923077,
|
| 239 |
+
"acc_stderr": 0.030236389942173106,
|
| 240 |
+
"acc_norm": 0.3076923076923077,
|
| 241 |
+
"acc_norm_stderr": 0.030236389942173106
|
| 242 |
+
},
|
| 243 |
+
"hendrycksTest-medical_genetics": {
|
| 244 |
+
"acc": 0.44,
|
| 245 |
+
"acc_stderr": 0.04988876515698589,
|
| 246 |
+
"acc_norm": 0.44,
|
| 247 |
+
"acc_norm_stderr": 0.04988876515698589
|
| 248 |
+
},
|
| 249 |
+
"hendrycksTest-miscellaneous": {
|
| 250 |
+
"acc": 0.26947637292464877,
|
| 251 |
+
"acc_stderr": 0.015866243073215068,
|
| 252 |
+
"acc_norm": 0.26947637292464877,
|
| 253 |
+
"acc_norm_stderr": 0.015866243073215068
|
| 254 |
+
},
|
| 255 |
+
"hendrycksTest-moral_disputes": {
|
| 256 |
+
"acc": 0.30346820809248554,
|
| 257 |
+
"acc_stderr": 0.024752411960917212,
|
| 258 |
+
"acc_norm": 0.30346820809248554,
|
| 259 |
+
"acc_norm_stderr": 0.024752411960917212
|
| 260 |
+
},
|
| 261 |
+
"hendrycksTest-moral_scenarios": {
|
| 262 |
+
"acc": 0.23798882681564246,
|
| 263 |
+
"acc_stderr": 0.014242630070574915,
|
| 264 |
+
"acc_norm": 0.23798882681564246,
|
| 265 |
+
"acc_norm_stderr": 0.014242630070574915
|
| 266 |
+
},
|
| 267 |
+
"hendrycksTest-nutrition": {
|
| 268 |
+
"acc": 0.2549019607843137,
|
| 269 |
+
"acc_stderr": 0.024954184324879905,
|
| 270 |
+
"acc_norm": 0.2549019607843137,
|
| 271 |
+
"acc_norm_stderr": 0.024954184324879905
|
| 272 |
+
},
|
| 273 |
+
"hendrycksTest-philosophy": {
|
| 274 |
+
"acc": 0.2990353697749196,
|
| 275 |
+
"acc_stderr": 0.026003301117885142,
|
| 276 |
+
"acc_norm": 0.2990353697749196,
|
| 277 |
+
"acc_norm_stderr": 0.026003301117885142
|
| 278 |
+
},
|
| 279 |
+
"hendrycksTest-prehistory": {
|
| 280 |
+
"acc": 0.3117283950617284,
|
| 281 |
+
"acc_stderr": 0.02577311116963045,
|
| 282 |
+
"acc_norm": 0.3117283950617284,
|
| 283 |
+
"acc_norm_stderr": 0.02577311116963045
|
| 284 |
+
},
|
| 285 |
+
"hendrycksTest-professional_accounting": {
|
| 286 |
+
"acc": 0.2624113475177305,
|
| 287 |
+
"acc_stderr": 0.026244920349843007,
|
| 288 |
+
"acc_norm": 0.2624113475177305,
|
| 289 |
+
"acc_norm_stderr": 0.026244920349843007
|
| 290 |
+
},
|
| 291 |
+
"hendrycksTest-professional_law": {
|
| 292 |
+
"acc": 0.2803129074315515,
|
| 293 |
+
"acc_stderr": 0.01147155594495862,
|
| 294 |
+
"acc_norm": 0.2803129074315515,
|
| 295 |
+
"acc_norm_stderr": 0.01147155594495862
|
| 296 |
+
},
|
| 297 |
+
"hendrycksTest-professional_medicine": {
|
| 298 |
+
"acc": 0.19852941176470587,
|
| 299 |
+
"acc_stderr": 0.0242310133705411,
|
| 300 |
+
"acc_norm": 0.19852941176470587,
|
| 301 |
+
"acc_norm_stderr": 0.0242310133705411
|
| 302 |
+
},
|
| 303 |
+
"hendrycksTest-professional_psychology": {
|
| 304 |
+
"acc": 0.3088235294117647,
|
| 305 |
+
"acc_stderr": 0.01869085027359529,
|
| 306 |
+
"acc_norm": 0.3088235294117647,
|
| 307 |
+
"acc_norm_stderr": 0.01869085027359529
|
| 308 |
+
},
|
| 309 |
+
"hendrycksTest-public_relations": {
|
| 310 |
+
"acc": 0.3181818181818182,
|
| 311 |
+
"acc_stderr": 0.04461272175910508,
|
| 312 |
+
"acc_norm": 0.3181818181818182,
|
| 313 |
+
"acc_norm_stderr": 0.04461272175910508
|
| 314 |
+
},
|
| 315 |
+
"hendrycksTest-security_studies": {
|
| 316 |
+
"acc": 0.21224489795918366,
|
| 317 |
+
"acc_stderr": 0.026176967197866767,
|
| 318 |
+
"acc_norm": 0.21224489795918366,
|
| 319 |
+
"acc_norm_stderr": 0.026176967197866767
|
| 320 |
+
},
|
| 321 |
+
"hendrycksTest-sociology": {
|
| 322 |
+
"acc": 0.2736318407960199,
|
| 323 |
+
"acc_stderr": 0.031524391865554,
|
| 324 |
+
"acc_norm": 0.2736318407960199,
|
| 325 |
+
"acc_norm_stderr": 0.031524391865554
|
| 326 |
+
},
|
| 327 |
+
"hendrycksTest-us_foreign_policy": {
|
| 328 |
+
"acc": 0.28,
|
| 329 |
+
"acc_stderr": 0.04512608598542128,
|
| 330 |
+
"acc_norm": 0.28,
|
| 331 |
+
"acc_norm_stderr": 0.04512608598542128
|
| 332 |
+
},
|
| 333 |
+
"hendrycksTest-virology": {
|
| 334 |
+
"acc": 0.30120481927710846,
|
| 335 |
+
"acc_stderr": 0.035716092300534796,
|
| 336 |
+
"acc_norm": 0.30120481927710846,
|
| 337 |
+
"acc_norm_stderr": 0.035716092300534796
|
| 338 |
+
},
|
| 339 |
+
"hendrycksTest-world_religions": {
|
| 340 |
+
"acc": 0.38596491228070173,
|
| 341 |
+
"acc_stderr": 0.03733756969066164,
|
| 342 |
+
"acc_norm": 0.38596491228070173,
|
| 343 |
+
"acc_norm_stderr": 0.03733756969066164
|
| 344 |
+
}
|
| 345 |
+
},
|
| 346 |
+
"versions": {
|
| 347 |
+
"hendrycksTest-abstract_algebra": 1,
|
| 348 |
+
"hendrycksTest-anatomy": 1,
|
| 349 |
+
"hendrycksTest-astronomy": 1,
|
| 350 |
+
"hendrycksTest-business_ethics": 1,
|
| 351 |
+
"hendrycksTest-clinical_knowledge": 1,
|
| 352 |
+
"hendrycksTest-college_biology": 1,
|
| 353 |
+
"hendrycksTest-college_chemistry": 1,
|
| 354 |
+
"hendrycksTest-college_computer_science": 1,
|
| 355 |
+
"hendrycksTest-college_mathematics": 1,
|
| 356 |
+
"hendrycksTest-college_medicine": 1,
|
| 357 |
+
"hendrycksTest-college_physics": 1,
|
| 358 |
+
"hendrycksTest-computer_security": 1,
|
| 359 |
+
"hendrycksTest-conceptual_physics": 1,
|
| 360 |
+
"hendrycksTest-econometrics": 1,
|
| 361 |
+
"hendrycksTest-electrical_engineering": 1,
|
| 362 |
+
"hendrycksTest-elementary_mathematics": 1,
|
| 363 |
+
"hendrycksTest-formal_logic": 1,
|
| 364 |
+
"hendrycksTest-global_facts": 1,
|
| 365 |
+
"hendrycksTest-high_school_biology": 1,
|
| 366 |
+
"hendrycksTest-high_school_chemistry": 1,
|
| 367 |
+
"hendrycksTest-high_school_computer_science": 1,
|
| 368 |
+
"hendrycksTest-high_school_european_history": 1,
|
| 369 |
+
"hendrycksTest-high_school_geography": 1,
|
| 370 |
+
"hendrycksTest-high_school_government_and_politics": 1,
|
| 371 |
+
"hendrycksTest-high_school_macroeconomics": 1,
|
| 372 |
+
"hendrycksTest-high_school_mathematics": 1,
|
| 373 |
+
"hendrycksTest-high_school_microeconomics": 1,
|
| 374 |
+
"hendrycksTest-high_school_physics": 1,
|
| 375 |
+
"hendrycksTest-high_school_psychology": 1,
|
| 376 |
+
"hendrycksTest-high_school_statistics": 1,
|
| 377 |
+
"hendrycksTest-high_school_us_history": 1,
|
| 378 |
+
"hendrycksTest-high_school_world_history": 1,
|
| 379 |
+
"hendrycksTest-human_aging": 1,
|
| 380 |
+
"hendrycksTest-human_sexuality": 1,
|
| 381 |
+
"hendrycksTest-international_law": 1,
|
| 382 |
+
"hendrycksTest-jurisprudence": 1,
|
| 383 |
+
"hendrycksTest-logical_fallacies": 1,
|
| 384 |
+
"hendrycksTest-machine_learning": 1,
|
| 385 |
+
"hendrycksTest-management": 1,
|
| 386 |
+
"hendrycksTest-marketing": 1,
|
| 387 |
+
"hendrycksTest-medical_genetics": 1,
|
| 388 |
+
"hendrycksTest-miscellaneous": 1,
|
| 389 |
+
"hendrycksTest-moral_disputes": 1,
|
| 390 |
+
"hendrycksTest-moral_scenarios": 1,
|
| 391 |
+
"hendrycksTest-nutrition": 1,
|
| 392 |
+
"hendrycksTest-philosophy": 1,
|
| 393 |
+
"hendrycksTest-prehistory": 1,
|
| 394 |
+
"hendrycksTest-professional_accounting": 1,
|
| 395 |
+
"hendrycksTest-professional_law": 1,
|
| 396 |
+
"hendrycksTest-professional_medicine": 1,
|
| 397 |
+
"hendrycksTest-professional_psychology": 1,
|
| 398 |
+
"hendrycksTest-public_relations": 1,
|
| 399 |
+
"hendrycksTest-security_studies": 1,
|
| 400 |
+
"hendrycksTest-sociology": 1,
|
| 401 |
+
"hendrycksTest-us_foreign_policy": 1,
|
| 402 |
+
"hendrycksTest-virology": 1,
|
| 403 |
+
"hendrycksTest-world_religions": 1
|
| 404 |
+
},
|
| 405 |
+
"config": {
|
| 406 |
+
"model": "hf-causal",
|
| 407 |
+
"model_args": "pretrained=workdir_7b/ckpt_349",
|
| 408 |
+
"num_fewshot": 5,
|
| 409 |
+
"batch_size": "8",
|
| 410 |
+
"batch_sizes": [],
|
| 411 |
+
"device": null,
|
| 412 |
+
"no_cache": true,
|
| 413 |
+
"limit": null,
|
| 414 |
+
"bootstrap_iters": 100000,
|
| 415 |
+
"description_dict": {}
|
| 416 |
+
}
|
| 417 |
+
}
|
eval_truthfulqa.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"truthfulqa_mc": {
|
| 4 |
+
"mc1": 0.20563035495716034,
|
| 5 |
+
"mc1_stderr": 0.014148482219460978,
|
| 6 |
+
"mc2": 0.3321670658810331,
|
| 7 |
+
"mc2_stderr": 0.01308219195188674
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
"versions": {
|
| 11 |
+
"truthfulqa_mc": 1
|
| 12 |
+
},
|
| 13 |
+
"config": {
|
| 14 |
+
"model": "hf-causal",
|
| 15 |
+
"model_args": "pretrained=workdir_7b/ckpt_349",
|
| 16 |
+
"num_fewshot": 0,
|
| 17 |
+
"batch_size": "32",
|
| 18 |
+
"batch_sizes": [],
|
| 19 |
+
"device": null,
|
| 20 |
+
"no_cache": true,
|
| 21 |
+
"limit": null,
|
| 22 |
+
"bootstrap_iters": 100000,
|
| 23 |
+
"description_dict": {}
|
| 24 |
+
}
|
| 25 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e25e2212f9d58f3f58501bf4be19d111bf65d62ad28f7f25a5b2db68c30aae7
|
| 3 |
+
size 9877992505
|
pytorch_model-00002-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4e8d56253b86998708d9d838563d4be27164d3fee9b92aa1cb060d741d24a46
|
| 3 |
+
size 9894804061
|
pytorch_model-00003-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee6637897814c703841b55321b26456f1cc664fbfc8914cd10d7fa2b83578632
|
| 3 |
+
size 7180992992
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 26953670656
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
| 329 |
+
}
|
| 330 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"model_max_length": 2048,
|
| 20 |
+
"pad_token": null,
|
| 21 |
+
"sp_model_kwargs": {},
|
| 22 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"__type": "AddedToken",
|
| 25 |
+
"content": "<unk>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|