eduagarcia commited on
Commit
7084d46
β€’
1 Parent(s): 559bd6b

more models to initial_queue.jsonl

Browse files
initial_queue.jsonl CHANGED
@@ -7,7 +7,12 @@
7
  {"model": "openlm-research/open_llama_3b_v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
8
  {"model": "openlm-research/open_llama_7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
9
  {"model": "openlm-research/open_llama_7b_v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
10
- // 2 - portuguese models
 
 
 
 
 
11
  {"model": "maritaca-ai/sabia-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
12
  {"model": "dominguesm/canarim-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
13
  {"model": "22h/open-cabrita3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
@@ -15,24 +20,16 @@
15
  {"model": "recogna-nlp/bode-13b-alpaca-pt-br", "base_model": "meta-llama/Llama-2-13b-chat-hf", "revision": "main", "precision": "float16", "weight_type": "Adapter", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
16
  {"model": "22h/cabrita_7b_pt_850000", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
17
  {"model": "22h/cabrita-lora-v0-1", "base_model": "huggyllama/llama-7b", "revision": "main", "precision": "float16", "weight_type": "Adapter", "model_type": "πŸ”Ά : fine-tuned"}
18
- {"model": "pierreguillou/gpt2-small-portuguese", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
19
- {"model": "pucpr/gpt2-bio-pt", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
20
- {"model": "unicamp-dl/ptt5-small-portuguese-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
21
- {"model": "unicamp-dl/ptt5-base-portuguese-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
22
- {"model": "unicamp-dl/ptt5-large-portuguese-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
23
- {"model": "unicamp-dl/ptt5-small-t5-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
24
- {"model": "unicamp-dl/ptt5-base-t5-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
25
- {"model": "unicamp-dl/ptt5-large-t5-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
26
- {"model": "josu/gpt-neo-pt-br", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
27
- {"model": "josu/gpt-neo-pt-1.3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
28
- {"model": "monilouise/opt125M_portuguese", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
29
- {"model": "HeyLucasLeao/gpt-neo-small-portuguese", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
30
- // 3 - Larger base models <= 13B
31
- {"model": "meta-llama/Llama-2-13b-hf", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
32
- {"model": "huggyllama/llama-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
33
- {"model": "openlm-research/open_llama_13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
34
- {"model": "upstage/SOLAR-10.7B-v1.0", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
35
  // other must-have <=7B
 
36
  {"model": "01-ai/Yi-6B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
37
  {"model": "Unbabel/TowerBase-7B-v0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
38
  {"model": "tiiuae/falcon-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
@@ -40,22 +37,22 @@
40
  {"model": "bigscience/bloom-1b7", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
41
  {"model": "bigscience/bloom-3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
42
  {"model": "bigscience/bloom-7b1", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
43
- {"model": "gpt2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
44
  {"model": "stabilityai/stablelm-2-1_6b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
45
  {"model": "stabilityai/stablelm-3b-4e1t", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
46
- {"model": "t5-small", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
47
- {"model": "t5-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
48
- {"model": "t5-large", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
49
- {"model": "google/mt5-small", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
50
- {"model": "google/mt5-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
51
- {"model": "google/mt5-large", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
52
  // Larger base models >13B
53
  {"model": "mistralai/Mixtral-8x7B-v0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
54
  {"model": "huggyllama/llama-30b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
55
  {"model": "01-ai/Yi-34B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
56
  {"model": "meta-llama/Llama-2-70b-hf", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "οΏ½οΏ½οΏ½ : pretrained"}
57
  {"model": "huggyllama/llama-65b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
58
- // others
 
 
 
 
 
 
 
59
  {"model": "internlm/internlm2-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ”Ά : fine-tuned"}
60
  {"model": "internlm/internlm2-base-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
61
  {"model": "internlm/internlm-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
@@ -65,11 +62,41 @@
65
  {"model": "Qwen/Qwen-1_8B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
66
  {"model": "Qwen/Qwen-7B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
67
  {"model": "Qwen/Qwen-14B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"model": "Qwen/Qwen-72B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
69
- {"model": "DAMO-NLP-MT/polylm-1.7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
70
- {"model": "DAMO-NLP-MT/polylm-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
71
- {"model": "Deci/DeciLM-6b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ”Ά : fine-tuned"}
72
- {"model": "Deci/DeciLM-7B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ”Ά : fine-tuned"}
 
 
 
 
 
 
 
 
 
 
 
73
  {"model": "EleutherAI/pythia-14m", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
74
  {"model": "EleutherAI/pythia-70m-deduped", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
75
  {"model": "EleutherAI/pythia-160m-deduped", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
@@ -85,7 +112,44 @@
85
  {"model": "facebook/opt-6.7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
86
  {"model": "facebook/opt-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
87
  {"model": "facebook/opt-30b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
88
  {"model": "facebook/opt-66b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  {"model": "EleutherAI/gpt-neo-125m", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
90
  {"model": "EleutherAI/gpt-neo-1.3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
91
  {"model": "EleutherAI/gpt-neo-2.7B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
@@ -95,7 +159,6 @@
95
  {"model": "stabilityai/stablelm-base-alpha-7b-v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
96
  {"model": "stabilityai/stablelm-base-alpha-3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
97
  {"model": "stabilityai/stablelm-base-alpha-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
98
- {"model": "tiiuae/falcon-40b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
99
  {"model": "openai-community/openai-gpt", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
100
  {"model": "openai-community/gpt2-medium", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
101
  {"model": "openai-community/gpt2-large", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
@@ -104,6 +167,8 @@
104
  {"model": "microsoft/phi-1_5", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
105
  {"model": "microsoft/phi-2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
106
  {"model": "mosaicml/mpt-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
 
107
  {"model": "01-ai/Yi-6B-200K", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
108
  {"model": "01-ai/Yi-34B-200K", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
109
  {"model": "google/t5-v1_1-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
@@ -140,3 +205,12 @@
140
  {"model": "EleutherAI/pythia-2.8b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
141
  {"model": "EleutherAI/pythia-6.9b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
142
  {"model": "EleutherAI/pythia-12b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
 
 
 
 
 
 
 
 
 
7
  {"model": "openlm-research/open_llama_3b_v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
8
  {"model": "openlm-research/open_llama_7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
9
  {"model": "openlm-research/open_llama_7b_v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
10
+ // 2 - Larger base models <= 13B
11
+ {"model": "meta-llama/Llama-2-13b-hf", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
12
+ {"model": "huggyllama/llama-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
13
+ {"model": "openlm-research/open_llama_13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
14
+ {"model": "upstage/SOLAR-10.7B-v1.0", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
15
+ // 3 - portuguese models
16
  {"model": "maritaca-ai/sabia-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
17
  {"model": "dominguesm/canarim-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
18
  {"model": "22h/open-cabrita3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
 
20
  {"model": "recogna-nlp/bode-13b-alpaca-pt-br", "base_model": "meta-llama/Llama-2-13b-chat-hf", "revision": "main", "precision": "float16", "weight_type": "Adapter", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
21
  {"model": "22h/cabrita_7b_pt_850000", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
22
  {"model": "22h/cabrita-lora-v0-1", "base_model": "huggyllama/llama-7b", "revision": "main", "precision": "float16", "weight_type": "Adapter", "model_type": "πŸ”Ά : fine-tuned"}
23
+ {"model": "wandgibaut/periquito-3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
24
+ {"model": "nicolasdec/Cabra", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
25
+ {"model": "nicolasdec/cabra13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
26
+ {"model": "lrds-code/samba-1.1B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
27
+ {"model": "lrds-code/boana-7b-instruct", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
28
+ {"model": "nicholasKluge/Aira-2-portuguese-124M", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
29
+ {"model": "nicholasKluge/Aira-2-portuguese-560M", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
30
+ {"model": "nicholasKluge/Aira-2-portuguese-1B7", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
 
 
 
 
 
 
 
 
 
31
  // other must-have <=7B
32
+ {"model": "dynamofl/dynamo-8B-v0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
33
  {"model": "01-ai/Yi-6B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
34
  {"model": "Unbabel/TowerBase-7B-v0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
35
  {"model": "tiiuae/falcon-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
37
  {"model": "bigscience/bloom-1b7", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
38
  {"model": "bigscience/bloom-3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
39
  {"model": "bigscience/bloom-7b1", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
40
  {"model": "stabilityai/stablelm-2-1_6b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
41
  {"model": "stabilityai/stablelm-3b-4e1t", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
 
 
 
 
 
42
  // Larger base models >13B
43
  {"model": "mistralai/Mixtral-8x7B-v0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
44
  {"model": "huggyllama/llama-30b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
45
  {"model": "01-ai/Yi-34B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
46
  {"model": "meta-llama/Llama-2-70b-hf", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "οΏ½οΏ½οΏ½ : pretrained"}
47
  {"model": "huggyllama/llama-65b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
48
+ // minors must
49
+ {"model": "togethercomputer/RedPajama-INCITE-Base-3B-v1", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
50
+ {"model": "togethercomputer/RedPajama-INCITE-7B-Base", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
51
+ {"model": "DAMO-NLP-MT/polylm-1.7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
52
+ {"model": "DAMO-NLP-MT/polylm-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
53
+ {"model": "Deci/DeciLM-6b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ”Ά : fine-tuned"}
54
+ {"model": "Deci/DeciLM-7B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ”Ά : fine-tuned"}
55
+ // multiple (ch-jp)/en bi/multi lingual models
56
  {"model": "internlm/internlm2-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ”Ά : fine-tuned"}
57
  {"model": "internlm/internlm2-base-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
58
  {"model": "internlm/internlm-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
62
  {"model": "Qwen/Qwen-1_8B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
63
  {"model": "Qwen/Qwen-7B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
64
  {"model": "Qwen/Qwen-14B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
65
+ {"model": "xverse/XVERSE-7B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
66
+ {"model": "xverse/XVERSE-13B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
67
+ {"model": "xverse/XVERSE-13B-256K", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
68
+ {"model": "Skywork/Skywork-13B-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
69
+ {"model": "baichuan-inc/Baichuan-7B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
70
+ {"model": "baichuan-inc/Baichuan-13B-Base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
71
+ {"model": "baichuan-inc/Baichuan2-7B-Base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
72
+ {"model": "baichuan-inc/Baichuan2-13B-Base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
73
+ {"model": "OrionStarAI/Orion-14B-Base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
74
+ {"model": "deepseek-ai/deepseek-llm-7b-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
75
+ {"model": "deepseek-ai/deepseek-moe-16b-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
76
+ {"model": "BAAI/Aquila-7B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
77
+ {"model": "BAAI/Aquila2-7B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
78
+ {"model": "THUDM/chatglm3-6b-base", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
79
+ {"model": "THUDM/glm-2b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
80
+ {"model": "THUDM/glm-10b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
81
+ {"model": "fnlp/moss-moon-003-base", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
82
+ {"model": "fnlp/moss-base-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
83
+ // multiple chinese/jp large
84
  {"model": "Qwen/Qwen-72B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
85
+ {"model": "xverse/XVERSE-65B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
86
+ {"model": "xverse/XVERSE-65B-2", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
87
+ {"model": "deepseek-ai/deepseek-llm-67b-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
88
+ {"model": "BAAI/Aquila2-34B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
89
+ {"model": "BAAI/Aquila2-70B-Expr", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
90
+ // minors must 2
91
+ {"model": "gpt2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
92
+ {"model": "t5-small", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
93
+ {"model": "t5-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
94
+ {"model": "t5-large", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
95
+ {"model": "google/mt5-small", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
96
+ {"model": "google/mt5-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
97
+ {"model": "google/mt5-large", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
98
+ //others
99
+ {"model": "NucleusAI/nucleus-22B-token-500B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
100
  {"model": "EleutherAI/pythia-14m", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
101
  {"model": "EleutherAI/pythia-70m-deduped", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
102
  {"model": "EleutherAI/pythia-160m-deduped", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
112
  {"model": "facebook/opt-6.7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
113
  {"model": "facebook/opt-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
114
  {"model": "facebook/opt-30b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
115
+ //other large
116
  {"model": "facebook/opt-66b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
117
+ {"model": "tiiuae/falcon-40b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
118
+ // minors portuguese
119
+ {"model": "pierreguillou/gpt2-small-portuguese", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
120
+ {"model": "pucpr/gpt2-bio-pt", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
121
+ {"model": "unicamp-dl/ptt5-small-portuguese-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
122
+ {"model": "unicamp-dl/ptt5-base-portuguese-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
123
+ {"model": "unicamp-dl/ptt5-large-portuguese-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
124
+ {"model": "unicamp-dl/ptt5-small-t5-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
125
+ {"model": "unicamp-dl/ptt5-base-t5-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
126
+ {"model": "unicamp-dl/ptt5-large-t5-vocab", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
127
+ {"model": "josu/gpt-neo-pt-br", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
128
+ {"model": "josu/gpt-neo-pt-1.3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
129
+ {"model": "monilouise/opt125M_portuguese", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
130
+ {"model": "HeyLucasLeao/gpt-neo-small-portuguese", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
131
+ // other langs (es/Ko/Jp/nordic)
132
+ {"model": "projecte-aina/FLOR-760M", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
133
+ {"model": "projecte-aina/FLOR-1.3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
134
+ {"model": "projecte-aina/FLOR-6.3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
135
+ {"model": "projecte-aina/aguila-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
136
+ {"model": "EleutherAI/polyglot-ko-12.8b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
137
+ {"model": "matsuo-lab/weblab-10b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
138
+ {"model": "pfnet/plamo-13b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
139
+ {"model": "AI-Sweden-Models/gpt-sw3-6.7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
140
+ {"model": "AI-Sweden-Models/gpt-sw3-6.7b-v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
141
+ {"model": "AI-Sweden-Models/gpt-sw3-20b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
142
+ {"model": "AI-Sweden-Models/gpt-sw3-40b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
143
+ {"model": "AI-Sweden-Models/gpt-sw3-40b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
144
+ {"model": "OpenLLM-France/Claire-Mistral-7B-0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
145
+ {"model": "OpenLLM-France/Claire-7B-0.1", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ†Ž : language adapted models (FP, FT, ...)"}
146
+ // huge models:
147
+ //{"model": "bigscience/bloom", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
148
+ //{"model": "tiiuae/falcon-180B", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
149
+ //{"model": "facebook/galactica-120b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
150
+ //random chat models
151
+ {"model": "openchat/openchat-3.5-0106", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "πŸ’¬ : chat models (RLHF, DPO, IFT, ...)"}
152
+ //other 2
153
  {"model": "EleutherAI/gpt-neo-125m", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
154
  {"model": "EleutherAI/gpt-neo-1.3B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
155
  {"model": "EleutherAI/gpt-neo-2.7B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
159
  {"model": "stabilityai/stablelm-base-alpha-7b-v2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
160
  {"model": "stabilityai/stablelm-base-alpha-3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
161
  {"model": "stabilityai/stablelm-base-alpha-7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
162
  {"model": "openai-community/openai-gpt", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
163
  {"model": "openai-community/gpt2-medium", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
164
  {"model": "openai-community/gpt2-large", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
167
  {"model": "microsoft/phi-1_5", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
168
  {"model": "microsoft/phi-2", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
169
  {"model": "mosaicml/mpt-7b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
170
+ {"model": "mosaicml/mpt-30b", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
171
+ {"model": "mosaicml/mpt-7b-8k", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
172
  {"model": "01-ai/Yi-6B-200K", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
173
  {"model": "01-ai/Yi-34B-200K", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
174
  {"model": "google/t5-v1_1-base", "base_model": "", "revision": "main", "precision": "bfloat16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
 
205
  {"model": "EleutherAI/pythia-2.8b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
206
  {"model": "EleutherAI/pythia-6.9b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
207
  {"model": "EleutherAI/pythia-12b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
208
+ {"model": "facebook/galactica-125m", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
209
+ {"model": "facebook/galactica-1.3b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
210
+ {"model": "facebook/galactica-6.7b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
211
+ {"model": "facebook/galactica-30b", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
212
+ {"model": "facebook/xglm-564M", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
213
+ {"model": "facebook/xglm-1.7B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
214
+ {"model": "facebook/xglm-2.9B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
215
+ {"model": "facebook/xglm-4.5B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
216
+ {"model": "facebook/xglm-7.5B", "base_model": "", "revision": "main", "precision": "float16", "weight_type": "Original", "model_type": "🟒 : pretrained"}
requirements.txt CHANGED
@@ -13,7 +13,7 @@ python-dateutil==2.8.2
13
  requests==2.28.2
14
  sentencepiece
15
  tqdm==4.65.0
16
- transformers==4.36.0
17
  tokenizers>=0.15.0
18
  tiktoken>=0.5.2
19
  gradio-space-ci @ git+https://huggingface.co/spaces/Wauplin/gradio-space-ci@0.2.1 # CI !!!
 
13
  requests==2.28.2
14
  sentencepiece
15
  tqdm==4.65.0
16
+ transformers==4.37.1
17
  tokenizers>=0.15.0
18
  tiktoken>=0.5.2
19
  gradio-space-ci @ git+https://huggingface.co/spaces/Wauplin/gradio-space-ci@0.2.1 # CI !!!
src/submission/check_validity.py CHANGED
@@ -21,7 +21,10 @@ def check_model_card(repo_id: str) -> tuple[bool, str]:
21
  card = ModelCard.load(repo_id)
22
  except huggingface_hub.utils.EntryNotFoundError:
23
  return False, "Please add a model card to your model to explain how you trained/fine-tuned it.", None
24
-
 
 
 
25
  # Enforce license metadata
26
  if card.data.license is None:
27
  if not ("license_name" in card.data and "license_link" in card.data):
@@ -55,6 +58,7 @@ def is_model_on_hub(model_name: str, revision: str, token: str = None, trust_rem
55
  return True, None, config
56
 
57
  except ValueError as e:
 
58
  return (
59
  False,
60
  "needs to be launched with `trust_remote_code=True`. For safety reason, we do not allow these models to be automatically submitted to the leaderboard.",
 
21
  card = ModelCard.load(repo_id)
22
  except huggingface_hub.utils.EntryNotFoundError:
23
  return False, "Please add a model card to your model to explain how you trained/fine-tuned it.", None
24
+ except Exception as e:
25
+ traceback.print_exc()
26
+ return False, f"Error while loading the model card. Exception: {str(e)}", None
27
+
28
  # Enforce license metadata
29
  if card.data.license is None:
30
  if not ("license_name" in card.data and "license_link" in card.data):
 
58
  return True, None, config
59
 
60
  except ValueError as e:
61
+ traceback.print_exc()
62
  return (
63
  False,
64
  "needs to be launched with `trust_remote_code=True`. For safety reason, we do not allow these models to be automatically submitted to the leaderboard.",