Upload folder using huggingface_hub
Browse files- arc_challenge_25shot_bs16_bf16.json +25 -0
- config.json +25 -0
- gsm8k_5shot_bs16_bf16.json +23 -0
- hellaswag_10shot_bs16_bf16.json +25 -0
- humaneval_fp16.json +47 -0
- mmlu_5shot_bs4_bf16.json +417 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +330 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- truthfulqa_mc_0shot_bs16_bf16.json +25 -0
- winogrande_5shot_bs16_bf16.json +23 -0
arc_challenge_25shot_bs16_bf16.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"arc_challenge": {
|
4 |
+
"acc": 0.431740614334471,
|
5 |
+
"acc_stderr": 0.014474591427196206,
|
6 |
+
"acc_norm": 0.4539249146757679,
|
7 |
+
"acc_norm_stderr": 0.014549221105171864
|
8 |
+
}
|
9 |
+
},
|
10 |
+
"versions": {
|
11 |
+
"arc_challenge": 0
|
12 |
+
},
|
13 |
+
"config": {
|
14 |
+
"model": "sparseml",
|
15 |
+
"model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16",
|
16 |
+
"num_fewshot": 25,
|
17 |
+
"batch_size": "16",
|
18 |
+
"batch_sizes": [],
|
19 |
+
"device": "cuda:4",
|
20 |
+
"no_cache": true,
|
21 |
+
"limit": null,
|
22 |
+
"bootstrap_iters": 100000,
|
23 |
+
"description_dict": {}
|
24 |
+
}
|
25 |
+
}
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_bias": false,
|
3 |
+
"attention_dropout": 0.0,
|
4 |
+
"bos_token_id": 1,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"hidden_act": "silu",
|
7 |
+
"hidden_size": 4096,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"intermediate_size": 11008,
|
10 |
+
"max_position_embeddings": 4096,
|
11 |
+
"model_type": "llama",
|
12 |
+
"num_attention_heads": 32,
|
13 |
+
"num_hidden_layers": 32,
|
14 |
+
"num_key_value_heads": 32,
|
15 |
+
"pretraining_tp": 1,
|
16 |
+
"rms_norm_eps": 1e-05,
|
17 |
+
"rope_scaling": null,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
21 |
+
"transformers_version": "4.37.2",
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 32000,
|
24 |
+
"torch_dtype": "bfloat16"
|
25 |
+
}
|
gsm8k_5shot_bs16_bf16.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"gsm8k": {
|
4 |
+
"acc": 0.07960576194086429,
|
5 |
+
"acc_stderr": 0.00745592433867626
|
6 |
+
}
|
7 |
+
},
|
8 |
+
"versions": {
|
9 |
+
"gsm8k": 0
|
10 |
+
},
|
11 |
+
"config": {
|
12 |
+
"model": "sparseml",
|
13 |
+
"model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16",
|
14 |
+
"num_fewshot": 5,
|
15 |
+
"batch_size": "16",
|
16 |
+
"batch_sizes": [],
|
17 |
+
"device": "cuda:6",
|
18 |
+
"no_cache": true,
|
19 |
+
"limit": null,
|
20 |
+
"bootstrap_iters": 100000,
|
21 |
+
"description_dict": {}
|
22 |
+
}
|
23 |
+
}
|
hellaswag_10shot_bs16_bf16.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"hellaswag": {
|
4 |
+
"acc": 0.5493925512846046,
|
5 |
+
"acc_stderr": 0.004965375341643134,
|
6 |
+
"acc_norm": 0.7405895239992033,
|
7 |
+
"acc_norm_stderr": 0.004374153847826759
|
8 |
+
}
|
9 |
+
},
|
10 |
+
"versions": {
|
11 |
+
"hellaswag": 0
|
12 |
+
},
|
13 |
+
"config": {
|
14 |
+
"model": "sparseml",
|
15 |
+
"model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16",
|
16 |
+
"num_fewshot": 10,
|
17 |
+
"batch_size": "16",
|
18 |
+
"batch_sizes": [],
|
19 |
+
"device": "cuda:2",
|
20 |
+
"no_cache": true,
|
21 |
+
"limit": null,
|
22 |
+
"bootstrap_iters": 100000,
|
23 |
+
"description_dict": {}
|
24 |
+
}
|
25 |
+
}
|
humaneval_fp16.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"humaneval": {
|
3 |
+
"pass@1": 0.14402439024390246,
|
4 |
+
"pass@10": 0.19110161217231836
|
5 |
+
},
|
6 |
+
"config": {
|
7 |
+
"prefix": "",
|
8 |
+
"do_sample": true,
|
9 |
+
"temperature": 0.2,
|
10 |
+
"top_k": 0,
|
11 |
+
"top_p": 0.95,
|
12 |
+
"n_samples": 50,
|
13 |
+
"eos": "<|endoftext|>",
|
14 |
+
"seed": 0,
|
15 |
+
"model": "/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint",
|
16 |
+
"modeltype": "causal",
|
17 |
+
"peft_model": null,
|
18 |
+
"revision": null,
|
19 |
+
"use_auth_token": false,
|
20 |
+
"trust_remote_code": false,
|
21 |
+
"tasks": "humaneval",
|
22 |
+
"instruction_tokens": null,
|
23 |
+
"batch_size": 32,
|
24 |
+
"max_length_generation": 512,
|
25 |
+
"precision": "fp16",
|
26 |
+
"load_in_8bit": false,
|
27 |
+
"load_in_4bit": false,
|
28 |
+
"left_padding": false,
|
29 |
+
"limit": null,
|
30 |
+
"limit_start": 0,
|
31 |
+
"save_every_k_tasks": -1,
|
32 |
+
"postprocess": true,
|
33 |
+
"allow_code_execution": true,
|
34 |
+
"generation_only": false,
|
35 |
+
"load_generations_path": null,
|
36 |
+
"load_data_path": null,
|
37 |
+
"metric_output_path": "/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint/humaneval_fp16.json",
|
38 |
+
"save_generations": true,
|
39 |
+
"load_generations_intermediate_paths": null,
|
40 |
+
"save_generations_path": "generations.json",
|
41 |
+
"save_references": false,
|
42 |
+
"save_references_path": "references.json",
|
43 |
+
"prompt": "prompt",
|
44 |
+
"max_memory_per_gpu": "auto",
|
45 |
+
"check_references": false
|
46 |
+
}
|
47 |
+
}
|
mmlu_5shot_bs4_bf16.json
ADDED
@@ -0,0 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"hendrycksTest-abstract_algebra": {
|
4 |
+
"acc": 0.27,
|
5 |
+
"acc_stderr": 0.04461960433384741,
|
6 |
+
"acc_norm": 0.27,
|
7 |
+
"acc_norm_stderr": 0.04461960433384741
|
8 |
+
},
|
9 |
+
"hendrycksTest-anatomy": {
|
10 |
+
"acc": 0.3925925925925926,
|
11 |
+
"acc_stderr": 0.04218506215368879,
|
12 |
+
"acc_norm": 0.3925925925925926,
|
13 |
+
"acc_norm_stderr": 0.04218506215368879
|
14 |
+
},
|
15 |
+
"hendrycksTest-astronomy": {
|
16 |
+
"acc": 0.3815789473684211,
|
17 |
+
"acc_stderr": 0.03953173377749194,
|
18 |
+
"acc_norm": 0.3815789473684211,
|
19 |
+
"acc_norm_stderr": 0.03953173377749194
|
20 |
+
},
|
21 |
+
"hendrycksTest-business_ethics": {
|
22 |
+
"acc": 0.4,
|
23 |
+
"acc_stderr": 0.049236596391733084,
|
24 |
+
"acc_norm": 0.4,
|
25 |
+
"acc_norm_stderr": 0.049236596391733084
|
26 |
+
},
|
27 |
+
"hendrycksTest-clinical_knowledge": {
|
28 |
+
"acc": 0.37735849056603776,
|
29 |
+
"acc_stderr": 0.029832808114796005,
|
30 |
+
"acc_norm": 0.37735849056603776,
|
31 |
+
"acc_norm_stderr": 0.029832808114796005
|
32 |
+
},
|
33 |
+
"hendrycksTest-college_biology": {
|
34 |
+
"acc": 0.3680555555555556,
|
35 |
+
"acc_stderr": 0.040329990539607195,
|
36 |
+
"acc_norm": 0.3680555555555556,
|
37 |
+
"acc_norm_stderr": 0.040329990539607195
|
38 |
+
},
|
39 |
+
"hendrycksTest-college_chemistry": {
|
40 |
+
"acc": 0.25,
|
41 |
+
"acc_stderr": 0.04351941398892446,
|
42 |
+
"acc_norm": 0.25,
|
43 |
+
"acc_norm_stderr": 0.04351941398892446
|
44 |
+
},
|
45 |
+
"hendrycksTest-college_computer_science": {
|
46 |
+
"acc": 0.37,
|
47 |
+
"acc_stderr": 0.04852365870939099,
|
48 |
+
"acc_norm": 0.37,
|
49 |
+
"acc_norm_stderr": 0.04852365870939099
|
50 |
+
},
|
51 |
+
"hendrycksTest-college_mathematics": {
|
52 |
+
"acc": 0.3,
|
53 |
+
"acc_stderr": 0.046056618647183814,
|
54 |
+
"acc_norm": 0.3,
|
55 |
+
"acc_norm_stderr": 0.046056618647183814
|
56 |
+
},
|
57 |
+
"hendrycksTest-college_medicine": {
|
58 |
+
"acc": 0.3236994219653179,
|
59 |
+
"acc_stderr": 0.0356760379963917,
|
60 |
+
"acc_norm": 0.3236994219653179,
|
61 |
+
"acc_norm_stderr": 0.0356760379963917
|
62 |
+
},
|
63 |
+
"hendrycksTest-college_physics": {
|
64 |
+
"acc": 0.22549019607843138,
|
65 |
+
"acc_stderr": 0.04158307533083286,
|
66 |
+
"acc_norm": 0.22549019607843138,
|
67 |
+
"acc_norm_stderr": 0.04158307533083286
|
68 |
+
},
|
69 |
+
"hendrycksTest-computer_security": {
|
70 |
+
"acc": 0.46,
|
71 |
+
"acc_stderr": 0.05009082659620332,
|
72 |
+
"acc_norm": 0.46,
|
73 |
+
"acc_norm_stderr": 0.05009082659620332
|
74 |
+
},
|
75 |
+
"hendrycksTest-conceptual_physics": {
|
76 |
+
"acc": 0.33617021276595743,
|
77 |
+
"acc_stderr": 0.03088161852067694,
|
78 |
+
"acc_norm": 0.33617021276595743,
|
79 |
+
"acc_norm_stderr": 0.03088161852067694
|
80 |
+
},
|
81 |
+
"hendrycksTest-econometrics": {
|
82 |
+
"acc": 0.3157894736842105,
|
83 |
+
"acc_stderr": 0.04372748290278007,
|
84 |
+
"acc_norm": 0.3157894736842105,
|
85 |
+
"acc_norm_stderr": 0.04372748290278007
|
86 |
+
},
|
87 |
+
"hendrycksTest-electrical_engineering": {
|
88 |
+
"acc": 0.3793103448275862,
|
89 |
+
"acc_stderr": 0.04043461861916747,
|
90 |
+
"acc_norm": 0.3793103448275862,
|
91 |
+
"acc_norm_stderr": 0.04043461861916747
|
92 |
+
},
|
93 |
+
"hendrycksTest-elementary_mathematics": {
|
94 |
+
"acc": 0.25925925925925924,
|
95 |
+
"acc_stderr": 0.02256989707491841,
|
96 |
+
"acc_norm": 0.25925925925925924,
|
97 |
+
"acc_norm_stderr": 0.02256989707491841
|
98 |
+
},
|
99 |
+
"hendrycksTest-formal_logic": {
|
100 |
+
"acc": 0.20634920634920634,
|
101 |
+
"acc_stderr": 0.03619604524124251,
|
102 |
+
"acc_norm": 0.20634920634920634,
|
103 |
+
"acc_norm_stderr": 0.03619604524124251
|
104 |
+
},
|
105 |
+
"hendrycksTest-global_facts": {
|
106 |
+
"acc": 0.3,
|
107 |
+
"acc_stderr": 0.046056618647183814,
|
108 |
+
"acc_norm": 0.3,
|
109 |
+
"acc_norm_stderr": 0.046056618647183814
|
110 |
+
},
|
111 |
+
"hendrycksTest-high_school_biology": {
|
112 |
+
"acc": 0.34838709677419355,
|
113 |
+
"acc_stderr": 0.02710482632810094,
|
114 |
+
"acc_norm": 0.34838709677419355,
|
115 |
+
"acc_norm_stderr": 0.02710482632810094
|
116 |
+
},
|
117 |
+
"hendrycksTest-high_school_chemistry": {
|
118 |
+
"acc": 0.3054187192118227,
|
119 |
+
"acc_stderr": 0.03240661565868408,
|
120 |
+
"acc_norm": 0.3054187192118227,
|
121 |
+
"acc_norm_stderr": 0.03240661565868408
|
122 |
+
},
|
123 |
+
"hendrycksTest-high_school_computer_science": {
|
124 |
+
"acc": 0.35,
|
125 |
+
"acc_stderr": 0.047937248544110196,
|
126 |
+
"acc_norm": 0.35,
|
127 |
+
"acc_norm_stderr": 0.047937248544110196
|
128 |
+
},
|
129 |
+
"hendrycksTest-high_school_european_history": {
|
130 |
+
"acc": 0.36363636363636365,
|
131 |
+
"acc_stderr": 0.03756335775187896,
|
132 |
+
"acc_norm": 0.36363636363636365,
|
133 |
+
"acc_norm_stderr": 0.03756335775187896
|
134 |
+
},
|
135 |
+
"hendrycksTest-high_school_geography": {
|
136 |
+
"acc": 0.3686868686868687,
|
137 |
+
"acc_stderr": 0.03437305501980619,
|
138 |
+
"acc_norm": 0.3686868686868687,
|
139 |
+
"acc_norm_stderr": 0.03437305501980619
|
140 |
+
},
|
141 |
+
"hendrycksTest-high_school_government_and_politics": {
|
142 |
+
"acc": 0.5181347150259067,
|
143 |
+
"acc_stderr": 0.036060650018329185,
|
144 |
+
"acc_norm": 0.5181347150259067,
|
145 |
+
"acc_norm_stderr": 0.036060650018329185
|
146 |
+
},
|
147 |
+
"hendrycksTest-high_school_macroeconomics": {
|
148 |
+
"acc": 0.34102564102564104,
|
149 |
+
"acc_stderr": 0.024035489676335068,
|
150 |
+
"acc_norm": 0.34102564102564104,
|
151 |
+
"acc_norm_stderr": 0.024035489676335068
|
152 |
+
},
|
153 |
+
"hendrycksTest-high_school_mathematics": {
|
154 |
+
"acc": 0.2851851851851852,
|
155 |
+
"acc_stderr": 0.027528599210340496,
|
156 |
+
"acc_norm": 0.2851851851851852,
|
157 |
+
"acc_norm_stderr": 0.027528599210340496
|
158 |
+
},
|
159 |
+
"hendrycksTest-high_school_microeconomics": {
|
160 |
+
"acc": 0.35294117647058826,
|
161 |
+
"acc_stderr": 0.03104194130405927,
|
162 |
+
"acc_norm": 0.35294117647058826,
|
163 |
+
"acc_norm_stderr": 0.03104194130405927
|
164 |
+
},
|
165 |
+
"hendrycksTest-high_school_physics": {
|
166 |
+
"acc": 0.31125827814569534,
|
167 |
+
"acc_stderr": 0.03780445850526732,
|
168 |
+
"acc_norm": 0.31125827814569534,
|
169 |
+
"acc_norm_stderr": 0.03780445850526732
|
170 |
+
},
|
171 |
+
"hendrycksTest-high_school_psychology": {
|
172 |
+
"acc": 0.4018348623853211,
|
173 |
+
"acc_stderr": 0.02102010617299701,
|
174 |
+
"acc_norm": 0.4018348623853211,
|
175 |
+
"acc_norm_stderr": 0.02102010617299701
|
176 |
+
},
|
177 |
+
"hendrycksTest-high_school_statistics": {
|
178 |
+
"acc": 0.3148148148148148,
|
179 |
+
"acc_stderr": 0.03167468706828979,
|
180 |
+
"acc_norm": 0.3148148148148148,
|
181 |
+
"acc_norm_stderr": 0.03167468706828979
|
182 |
+
},
|
183 |
+
"hendrycksTest-high_school_us_history": {
|
184 |
+
"acc": 0.37254901960784315,
|
185 |
+
"acc_stderr": 0.033933885849584025,
|
186 |
+
"acc_norm": 0.37254901960784315,
|
187 |
+
"acc_norm_stderr": 0.033933885849584025
|
188 |
+
},
|
189 |
+
"hendrycksTest-high_school_world_history": {
|
190 |
+
"acc": 0.4345991561181435,
|
191 |
+
"acc_stderr": 0.03226759995510144,
|
192 |
+
"acc_norm": 0.4345991561181435,
|
193 |
+
"acc_norm_stderr": 0.03226759995510144
|
194 |
+
},
|
195 |
+
"hendrycksTest-human_aging": {
|
196 |
+
"acc": 0.42152466367713004,
|
197 |
+
"acc_stderr": 0.03314190222110658,
|
198 |
+
"acc_norm": 0.42152466367713004,
|
199 |
+
"acc_norm_stderr": 0.03314190222110658
|
200 |
+
},
|
201 |
+
"hendrycksTest-human_sexuality": {
|
202 |
+
"acc": 0.3969465648854962,
|
203 |
+
"acc_stderr": 0.04291135671009224,
|
204 |
+
"acc_norm": 0.3969465648854962,
|
205 |
+
"acc_norm_stderr": 0.04291135671009224
|
206 |
+
},
|
207 |
+
"hendrycksTest-international_law": {
|
208 |
+
"acc": 0.5371900826446281,
|
209 |
+
"acc_stderr": 0.04551711196104218,
|
210 |
+
"acc_norm": 0.5371900826446281,
|
211 |
+
"acc_norm_stderr": 0.04551711196104218
|
212 |
+
},
|
213 |
+
"hendrycksTest-jurisprudence": {
|
214 |
+
"acc": 0.35185185185185186,
|
215 |
+
"acc_stderr": 0.046166311118017146,
|
216 |
+
"acc_norm": 0.35185185185185186,
|
217 |
+
"acc_norm_stderr": 0.046166311118017146
|
218 |
+
},
|
219 |
+
"hendrycksTest-logical_fallacies": {
|
220 |
+
"acc": 0.3374233128834356,
|
221 |
+
"acc_stderr": 0.037149084099355745,
|
222 |
+
"acc_norm": 0.3374233128834356,
|
223 |
+
"acc_norm_stderr": 0.037149084099355745
|
224 |
+
},
|
225 |
+
"hendrycksTest-machine_learning": {
|
226 |
+
"acc": 0.2857142857142857,
|
227 |
+
"acc_stderr": 0.042878587513404544,
|
228 |
+
"acc_norm": 0.2857142857142857,
|
229 |
+
"acc_norm_stderr": 0.042878587513404544
|
230 |
+
},
|
231 |
+
"hendrycksTest-management": {
|
232 |
+
"acc": 0.36893203883495146,
|
233 |
+
"acc_stderr": 0.04777615181156739,
|
234 |
+
"acc_norm": 0.36893203883495146,
|
235 |
+
"acc_norm_stderr": 0.04777615181156739
|
236 |
+
},
|
237 |
+
"hendrycksTest-marketing": {
|
238 |
+
"acc": 0.45726495726495725,
|
239 |
+
"acc_stderr": 0.03263622596380688,
|
240 |
+
"acc_norm": 0.45726495726495725,
|
241 |
+
"acc_norm_stderr": 0.03263622596380688
|
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": 0.4763729246487867,
|
251 |
+
"acc_stderr": 0.01785998976517645,
|
252 |
+
"acc_norm": 0.4763729246487867,
|
253 |
+
"acc_norm_stderr": 0.01785998976517645
|
254 |
+
},
|
255 |
+
"hendrycksTest-moral_disputes": {
|
256 |
+
"acc": 0.3699421965317919,
|
257 |
+
"acc_stderr": 0.025992472029306386,
|
258 |
+
"acc_norm": 0.3699421965317919,
|
259 |
+
"acc_norm_stderr": 0.025992472029306386
|
260 |
+
},
|
261 |
+
"hendrycksTest-moral_scenarios": {
|
262 |
+
"acc": 0.23798882681564246,
|
263 |
+
"acc_stderr": 0.01424263007057488,
|
264 |
+
"acc_norm": 0.23798882681564246,
|
265 |
+
"acc_norm_stderr": 0.01424263007057488
|
266 |
+
},
|
267 |
+
"hendrycksTest-nutrition": {
|
268 |
+
"acc": 0.4150326797385621,
|
269 |
+
"acc_stderr": 0.028213504177824103,
|
270 |
+
"acc_norm": 0.4150326797385621,
|
271 |
+
"acc_norm_stderr": 0.028213504177824103
|
272 |
+
},
|
273 |
+
"hendrycksTest-philosophy": {
|
274 |
+
"acc": 0.4405144694533762,
|
275 |
+
"acc_stderr": 0.028196400574197426,
|
276 |
+
"acc_norm": 0.4405144694533762,
|
277 |
+
"acc_norm_stderr": 0.028196400574197426
|
278 |
+
},
|
279 |
+
"hendrycksTest-prehistory": {
|
280 |
+
"acc": 0.37962962962962965,
|
281 |
+
"acc_stderr": 0.02700252103451648,
|
282 |
+
"acc_norm": 0.37962962962962965,
|
283 |
+
"acc_norm_stderr": 0.02700252103451648
|
284 |
+
},
|
285 |
+
"hendrycksTest-professional_accounting": {
|
286 |
+
"acc": 0.29432624113475175,
|
287 |
+
"acc_stderr": 0.02718712701150379,
|
288 |
+
"acc_norm": 0.29432624113475175,
|
289 |
+
"acc_norm_stderr": 0.02718712701150379
|
290 |
+
},
|
291 |
+
"hendrycksTest-professional_law": {
|
292 |
+
"acc": 0.30378096479791394,
|
293 |
+
"acc_stderr": 0.011745787720472472,
|
294 |
+
"acc_norm": 0.30378096479791394,
|
295 |
+
"acc_norm_stderr": 0.011745787720472472
|
296 |
+
},
|
297 |
+
"hendrycksTest-professional_medicine": {
|
298 |
+
"acc": 0.40808823529411764,
|
299 |
+
"acc_stderr": 0.029855261393483924,
|
300 |
+
"acc_norm": 0.40808823529411764,
|
301 |
+
"acc_norm_stderr": 0.029855261393483924
|
302 |
+
},
|
303 |
+
"hendrycksTest-professional_psychology": {
|
304 |
+
"acc": 0.35294117647058826,
|
305 |
+
"acc_stderr": 0.01933314202079706,
|
306 |
+
"acc_norm": 0.35294117647058826,
|
307 |
+
"acc_norm_stderr": 0.01933314202079706
|
308 |
+
},
|
309 |
+
"hendrycksTest-public_relations": {
|
310 |
+
"acc": 0.4090909090909091,
|
311 |
+
"acc_stderr": 0.04709306978661896,
|
312 |
+
"acc_norm": 0.4090909090909091,
|
313 |
+
"acc_norm_stderr": 0.04709306978661896
|
314 |
+
},
|
315 |
+
"hendrycksTest-security_studies": {
|
316 |
+
"acc": 0.3224489795918367,
|
317 |
+
"acc_stderr": 0.029923100563683906,
|
318 |
+
"acc_norm": 0.3224489795918367,
|
319 |
+
"acc_norm_stderr": 0.029923100563683906
|
320 |
+
},
|
321 |
+
"hendrycksTest-sociology": {
|
322 |
+
"acc": 0.42786069651741293,
|
323 |
+
"acc_stderr": 0.03498541988407795,
|
324 |
+
"acc_norm": 0.42786069651741293,
|
325 |
+
"acc_norm_stderr": 0.03498541988407795
|
326 |
+
},
|
327 |
+
"hendrycksTest-us_foreign_policy": {
|
328 |
+
"acc": 0.53,
|
329 |
+
"acc_stderr": 0.05016135580465919,
|
330 |
+
"acc_norm": 0.53,
|
331 |
+
"acc_norm_stderr": 0.05016135580465919
|
332 |
+
},
|
333 |
+
"hendrycksTest-virology": {
|
334 |
+
"acc": 0.3614457831325301,
|
335 |
+
"acc_stderr": 0.037400593820293204,
|
336 |
+
"acc_norm": 0.3614457831325301,
|
337 |
+
"acc_norm_stderr": 0.037400593820293204
|
338 |
+
},
|
339 |
+
"hendrycksTest-world_religions": {
|
340 |
+
"acc": 0.4678362573099415,
|
341 |
+
"acc_stderr": 0.038268824176603704,
|
342 |
+
"acc_norm": 0.4678362573099415,
|
343 |
+
"acc_norm_stderr": 0.038268824176603704
|
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": "sparseml",
|
407 |
+
"model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16",
|
408 |
+
"num_fewshot": 5,
|
409 |
+
"batch_size": "4",
|
410 |
+
"batch_sizes": [],
|
411 |
+
"device": "cuda:6",
|
412 |
+
"no_cache": true,
|
413 |
+
"limit": null,
|
414 |
+
"bootstrap_iters": 100000,
|
415 |
+
"description_dict": {}
|
416 |
+
}
|
417 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0baeb20300fab8e0972db24b3d53b567170aba6ab6178cb9a0871aa58a3b3050
|
3 |
+
size 4840431640
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b3817f91c9f327eff5b6859ec51d3068098659a1b32051d5127c0fcdd8f6c7d
|
3 |
+
size 4857209080
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42500e6de7da7b14930540f070b8dffdb0c22f387af2a7f1792be9e99b072951
|
3 |
+
size 4857209144
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd5c78c92f3daf76d0785e795b34b3488377046307f31371f060a5ea8cd8ebc6
|
3 |
+
size 4857209144
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e6cdd3ea3935eac10493aca463d9f4e2ce20cca5b759b6e08792b3fa2d59d0d
|
3 |
+
size 4857209144
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3070aef48703bf9cf656b2d72f7542badbf7c5421267d93496fef31cbf49daf0
|
3 |
+
size 2684439864
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26953670656
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
7 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
8 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
9 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
10 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
11 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
12 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
14 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
15 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
16 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
17 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
18 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
19 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
20 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
21 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
22 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
25 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
26 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
27 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
28 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
29 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
30 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
31 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
32 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
33 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
34 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
35 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
36 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
37 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
38 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
39 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
40 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
41 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
42 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
43 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
44 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
45 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
46 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
47 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
48 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
49 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
50 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
51 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
52 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
53 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
54 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
55 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
56 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
57 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
58 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
59 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
60 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
61 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
|
62 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
63 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
64 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
65 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
66 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
67 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
68 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
69 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
70 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
71 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
72 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
73 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
74 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
75 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
76 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
77 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
78 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
79 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
80 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
81 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
82 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
83 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
84 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
85 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
86 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
87 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
88 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
89 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
90 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
91 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
92 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
93 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
94 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
95 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
96 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
97 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
98 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
99 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
100 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
101 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
102 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
103 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
104 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
105 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
106 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
107 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
108 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
109 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
110 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
111 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
112 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
113 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
114 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
115 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
116 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
117 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
118 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
119 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
120 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
121 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
|
122 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
123 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
124 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
125 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
126 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
127 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
128 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
129 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
130 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
131 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
132 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
133 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
134 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
135 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
136 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
137 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
138 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
139 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
140 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
141 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
142 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
143 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
144 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
145 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
146 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
147 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
148 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
149 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
150 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
151 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
152 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
153 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
154 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
155 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
156 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
157 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
158 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
159 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
160 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
161 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
162 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
163 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
164 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
165 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
166 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
167 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
168 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
169 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
170 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
171 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
172 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
173 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
174 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
175 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
176 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
177 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
178 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
179 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
180 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
181 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
|
182 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
183 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
184 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
185 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
186 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
187 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
188 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
189 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
190 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
191 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
192 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
193 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
194 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
195 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
196 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
197 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
198 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
199 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
200 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
201 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
202 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
203 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
204 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
205 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
206 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
207 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
208 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
209 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
210 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
211 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
212 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
213 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
214 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
215 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
216 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
217 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
218 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
219 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
220 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
221 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
222 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
223 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
224 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
225 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
226 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
227 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
228 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
229 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
230 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
231 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
232 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
233 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
234 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
235 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
236 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
237 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
238 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
239 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
240 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
241 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
|
242 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
243 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
244 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
245 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
246 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
247 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
248 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
249 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
250 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
251 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
252 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
253 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
254 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
255 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
256 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
257 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
258 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
259 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
260 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
261 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
262 |
+
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
263 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
264 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
265 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
266 |
+
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
267 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
268 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
269 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
270 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
271 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
272 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
273 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
274 |
+
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
275 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
276 |
+
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
277 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
278 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
279 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
280 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
281 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
282 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
283 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
284 |
+
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
285 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
286 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
287 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
288 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
289 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
290 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
291 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
292 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
293 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
294 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
295 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
296 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
297 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
298 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
299 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
300 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
301 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
|
302 |
+
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
303 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
304 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
305 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
306 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
307 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
308 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
309 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
310 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
311 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
|
312 |
+
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
313 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
314 |
+
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
315 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
316 |
+
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
318 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
320 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
321 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
|
322 |
+
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
323 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
324 |
+
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
325 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
326 |
+
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
327 |
+
"model.norm.weight": "model-00006-of-00006.safetensors",
|
328 |
+
"lm_head.weight": "model-00006-of-00006.safetensors"
|
329 |
+
}
|
330 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
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 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": null,
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|
truthfulqa_mc_0shot_bs16_bf16.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"truthfulqa_mc": {
|
4 |
+
"mc1": 0.2350061199510404,
|
5 |
+
"mc1_stderr": 0.014843061507731618,
|
6 |
+
"mc2": 0.3668136165316701,
|
7 |
+
"mc2_stderr": 0.013583264391841515
|
8 |
+
}
|
9 |
+
},
|
10 |
+
"versions": {
|
11 |
+
"truthfulqa_mc": 1
|
12 |
+
},
|
13 |
+
"config": {
|
14 |
+
"model": "sparseml",
|
15 |
+
"model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16",
|
16 |
+
"num_fewshot": 0,
|
17 |
+
"batch_size": "16",
|
18 |
+
"batch_sizes": [],
|
19 |
+
"device": "cuda:4",
|
20 |
+
"no_cache": true,
|
21 |
+
"limit": null,
|
22 |
+
"bootstrap_iters": 100000,
|
23 |
+
"description_dict": {}
|
24 |
+
}
|
25 |
+
}
|
winogrande_5shot_bs16_bf16.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"results": {
|
3 |
+
"winogrande": {
|
4 |
+
"acc": 0.6945540647198106,
|
5 |
+
"acc_stderr": 0.012945038632552029
|
6 |
+
}
|
7 |
+
},
|
8 |
+
"versions": {
|
9 |
+
"winogrande": 0
|
10 |
+
},
|
11 |
+
"config": {
|
12 |
+
"model": "sparseml",
|
13 |
+
"model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/checkpoint,dtype=bfloat16",
|
14 |
+
"num_fewshot": 5,
|
15 |
+
"batch_size": "16",
|
16 |
+
"batch_sizes": [],
|
17 |
+
"device": "cuda:2",
|
18 |
+
"no_cache": true,
|
19 |
+
"limit": null,
|
20 |
+
"bootstrap_iters": 100000,
|
21 |
+
"description_dict": {}
|
22 |
+
}
|
23 |
+
}
|