Commit
•
9d5015b
1
Parent(s):
b323764
Update model types (#126)
Browse files- :speech_balloon: Update model types (c4f1532b4b97dc63a11437993219f896d0ed39e9)
Co-authored-by: Julien Launay <slippylolo@users.noreply.huggingface.co>
src/auto_leaderboard/model_metadata_type.py
CHANGED
@@ -17,153 +17,448 @@ class ModelType(Enum):
|
|
17 |
|
18 |
|
19 |
TYPE_METADATA: Dict[str, ModelType] = {
|
|
|
20 |
"aisquared/dlite-v1-355m": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
21 |
"aisquared/dlite-v2-774m": ModelType.SFT,
|
22 |
"aisquared/dlite-v2-1_5b": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
23 |
"TheBloke/wizardLM-7B-HF": ModelType.SFT,
|
|
|
|
|
|
|
24 |
"TheBloke/dromedary-65b-lora-HF": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
25 |
"TheBloke/vicuna-13B-1.1-HF": ModelType.SFT,
|
|
|
|
|
|
|
|
|
26 |
"TheBloke/Wizard-Vicuna-13B-Uncensored-HF": ModelType.SFT,
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
|
|
|
|
|
|
|
|
30 |
"AlekseyKorshuk/chatml-pyg-v1": ModelType.SFT,
|
|
|
31 |
"concedo/OPT-19M-ChatSalad": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"digitous/Javalion-R": ModelType.SFT,
|
|
|
33 |
"digitous/Alpacino30b": ModelType.SFT,
|
|
|
|
|
34 |
"digitous/Javelin-GPTJ": ModelType.SFT,
|
|
|
35 |
"anton-l/gpt-j-tiny-random": ModelType.SFT,
|
|
|
|
|
|
|
36 |
"IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1": ModelType.SFT,
|
|
|
|
|
37 |
"gpt2-medium": ModelType.PT,
|
|
|
|
|
38 |
"PygmalionAI/pygmalion-6b": ModelType.SFT,
|
|
|
|
|
|
|
|
|
39 |
"medalpaca/medalpaca-7b": ModelType.SFT,
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
|
|
|
|
|
|
44 |
"hakurei/lotus-12B": ModelType.SFT,
|
45 |
-
"amazon/LightGPT": ModelType.SFT,
|
46 |
"shibing624/chinese-llama-plus-13b-hf": ModelType.SFT,
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
"MetaIX/GPT4-X-Alpasta-30b": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
"EleutherAI/gpt-neox-20b": ModelType.PT,
|
|
|
|
|
|
|
|
|
52 |
"EleutherAI/gpt-j-6b": ModelType.PT,
|
53 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
"lmsys/vicuna-13b-delta-v1.1": ModelType.SFT,
|
55 |
"lmsys/vicuna-7b-delta-v1.1": ModelType.SFT,
|
56 |
"abhiramtirumala/DialoGPT-sarcastic-medium": ModelType.SFT,
|
|
|
|
|
|
|
57 |
"pillowtalks-ai/delta13b": ModelType.SFT,
|
|
|
|
|
58 |
"bigcode/starcoderplus": ModelType.SFT,
|
|
|
|
|
|
|
59 |
"microsoft/DialoGPT-large": ModelType.SFT,
|
|
|
|
|
60 |
"microsoft/CodeGPT-small-py": ModelType.SFT,
|
|
|
61 |
"Pirr/pythia-13b-deduped-green_devil": ModelType.SFT,
|
62 |
"Aeala/GPT4-x-AlpacaDente2-30b": ModelType.SFT,
|
|
|
|
|
63 |
"Aeala/VicUnlocked-alpaca-30b": ModelType.SFT,
|
64 |
-
"
|
|
|
|
|
65 |
"dvruette/oasst-gpt-neox-20b-1000-steps": ModelType.SFT,
|
66 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
"openlm-research/open_llama_7b_700bt_preview": ModelType.PT,
|
68 |
"openlm-research/open_llama_7b": ModelType.PT,
|
|
|
69 |
"openlm-research/open_llama_3b": ModelType.PT,
|
70 |
-
"openlm-research/
|
|
|
71 |
"PocketDoc/Dans-PileOfSets-Mk1-llama-13b-merged": ModelType.SFT,
|
72 |
-
"GeorgiaTechResearchInstitute/
|
|
|
73 |
"databricks/dolly-v2-7b": ModelType.SFT,
|
74 |
"databricks/dolly-v2-3b": ModelType.SFT,
|
75 |
"databricks/dolly-v2-12b": ModelType.SFT,
|
76 |
-
"pinkmanlove/llama-65b-hf": ModelType.SFT,
|
77 |
"Rachneet/gpt2-xl-alpaca": ModelType.SFT,
|
78 |
"Locutusque/gpt2-conversational-or-qa": ModelType.SFT,
|
|
|
79 |
"NbAiLab/nb-gpt-j-6B-alpaca": ModelType.SFT,
|
|
|
|
|
|
|
|
|
80 |
"Fredithefish/ScarletPajama-3B-HF": ModelType.SFT,
|
|
|
|
|
81 |
"eachadea/vicuna-7b-1.1": ModelType.SFT,
|
82 |
"eachadea/vicuna-13b": ModelType.SFT,
|
83 |
"openaccess-ai-collective/wizard-mega-13b": ModelType.SFT,
|
84 |
"openaccess-ai-collective/manticore-13b": ModelType.SFT,
|
85 |
"openaccess-ai-collective/manticore-30b-chat-pyg-alpha": ModelType.SFT,
|
86 |
"openaccess-ai-collective/minotaur-13b": ModelType.SFT,
|
87 |
-
"
|
|
|
|
|
88 |
"pythainlp/wangchanglm-7.5B-sft-enth": ModelType.SFT,
|
89 |
"pythainlp/wangchanglm-7.5B-sft-en-sharded": ModelType.SFT,
|
|
|
|
|
90 |
"stabilityai/stablelm-tuned-alpha-7b": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
91 |
"CalderaAI/30B-Lazarus": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
"KoboldAI/OPT-13B-Nerybus-Mix": ModelType.SFT,
|
93 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
"wahaha1987/llama_7b_sharegpt94k_fastchat": ModelType.SFT,
|
|
|
|
|
|
|
95 |
"OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5": ModelType.SFT,
|
|
|
|
|
|
|
96 |
"junelee/wizard-vicuna-13b": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
"BreadAi/StoryPy": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
"togethercomputer/RedPajama-INCITE-Base-3B-v1": ModelType.PT,
|
|
|
99 |
"togethercomputer/RedPajama-INCITE-Base-7B-v0.1": ModelType.PT,
|
|
|
|
|
|
|
|
|
|
|
100 |
"Writer/camel-5b-hf": ModelType.SFT,
|
101 |
"Writer/palmyra-base": ModelType.PT,
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
"MBZUAI/lamini-neo-125m": ModelType.SFT,
|
103 |
-
"TehVenom/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
"vicgalle/gpt2-alpaca-gpt4": ModelType.SFT,
|
105 |
"facebook/opt-350m": ModelType.PT,
|
106 |
"facebook/opt-125m": ModelType.PT,
|
|
|
|
|
|
|
|
|
107 |
"facebook/opt-13b": ModelType.PT,
|
108 |
-
"facebook/opt-1.3b": ModelType.PT,
|
109 |
"facebook/opt-66b": ModelType.PT,
|
110 |
-
"facebook/
|
111 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
112 |
"gpt2-xl": ModelType.PT,
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
|
|
|
|
|
|
116 |
"HuggingFaceH4/starchat-beta": ModelType.SFT,
|
117 |
-
"
|
|
|
|
|
|
|
|
|
118 |
"ausboss/llama-13b-supercot": ModelType.SFT,
|
119 |
"ausboss/llama-30b-supercot": ModelType.SFT,
|
120 |
"Neko-Institute-of-Science/metharme-7b": ModelType.SFT,
|
|
|
121 |
"SebastianSchramm/Cerebras-GPT-111M-instruction": ModelType.SFT,
|
122 |
"victor123/WizardLM-13B-1.0": ModelType.SFT,
|
123 |
-
"
|
124 |
-
"
|
125 |
"tiiuae/falcon-40b-instruct": ModelType.SFT,
|
126 |
"tiiuae/falcon-40b": ModelType.PT,
|
127 |
"tiiuae/falcon-7b": ModelType.PT,
|
128 |
-
"
|
129 |
-
"
|
|
|
|
|
|
|
130 |
"xzuyn/MedicWizard-7B": ModelType.SFT,
|
131 |
"beomi/KoAlpaca-Polyglot-5.8B": ModelType.SFT,
|
132 |
-
"
|
|
|
133 |
"Salesforce/codegen-16B-nl": ModelType.PT,
|
134 |
-
"Salesforce/codegen-
|
135 |
"ai-forever/rugpt3large_based_on_gpt2": ModelType.SFT,
|
136 |
"gpt2-large": ModelType.PT,
|
|
|
|
|
137 |
"huggingface/llama-13b": ModelType.PT,
|
138 |
"huggingface/llama-7b": ModelType.PT,
|
139 |
"huggingface/llama-65b": ModelType.PT,
|
|
|
140 |
"huggingface/llama-30b": ModelType.PT,
|
141 |
-
"
|
142 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
"cerebras/Cerebras-GPT-1.3B": ModelType.PT,
|
|
|
|
|
144 |
"cerebras/Cerebras-GPT-111M": ModelType.PT,
|
|
|
|
|
|
|
|
|
|
|
145 |
"NousResearch/Nous-Hermes-13b": ModelType.SFT,
|
146 |
"project-baize/baize-v2-7b": ModelType.SFT,
|
147 |
"project-baize/baize-v2-13b": ModelType.SFT,
|
|
|
148 |
"LLMs/AlpacaGPT4-7B-elina": ModelType.SFT,
|
149 |
-
"
|
|
|
|
|
150 |
"huggingtweets/jerma985": ModelType.SFT,
|
|
|
|
|
|
|
151 |
"huggyllama/llama-65b": ModelType.PT,
|
|
|
|
|
|
|
152 |
"WizardLM/WizardLM-13B-1.0": ModelType.SFT,
|
|
|
|
|
153 |
"gpt2": ModelType.PT,
|
154 |
-
"
|
|
|
|
|
|
|
|
|
155 |
"MayaPH/FinOPT-Lincoln": ModelType.SFT,
|
156 |
"MayaPH/FinOPT-Franklin": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
157 |
"timdettmers/guanaco-33b-merged": ModelType.SFT,
|
158 |
-
"timdettmers/guanaco-65b-merged": ModelType.SFT,
|
159 |
-
"elinas/llama-30b-hf-transformers-4.29": ModelType.SFT,
|
160 |
"elinas/chronos-33b": ModelType.SFT,
|
161 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
"xhyi/PT_GPTNEO350_ATG": ModelType.SFT,
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
"h2oai/h2ogpt-oasst1-512-20b": ModelType.SFT,
|
|
|
164 |
"h2oai/h2ogpt-gm-oasst1-en-1024-12b": ModelType.SFT,
|
165 |
-
"
|
166 |
-
"
|
|
|
|
|
|
|
167 |
}
|
168 |
|
169 |
|
|
|
17 |
|
18 |
|
19 |
TYPE_METADATA: Dict[str, ModelType] = {
|
20 |
+
"notstoic/PygmalionCoT-7b": ModelType.SFT,
|
21 |
"aisquared/dlite-v1-355m": ModelType.SFT,
|
22 |
+
"aisquared/dlite-v1-1_5b": ModelType.SFT,
|
23 |
+
"aisquared/dlite-v1-774m": ModelType.SFT,
|
24 |
+
"aisquared/dlite-v1-124m": ModelType.SFT,
|
25 |
+
"aisquared/chopt-2_7b": ModelType.SFT,
|
26 |
+
"aisquared/dlite-v2-124m": ModelType.SFT,
|
27 |
"aisquared/dlite-v2-774m": ModelType.SFT,
|
28 |
"aisquared/dlite-v2-1_5b": ModelType.SFT,
|
29 |
+
"aisquared/chopt-1_3b": ModelType.SFT,
|
30 |
+
"aisquared/dlite-v2-355m": ModelType.SFT,
|
31 |
+
"TheBloke/tulu-7B-fp16": ModelType.SFT,
|
32 |
+
"TheBloke/guanaco-7B-HF": ModelType.SFT,
|
33 |
+
"TheBloke/koala-7B-HF": ModelType.SFT,
|
34 |
"TheBloke/wizardLM-7B-HF": ModelType.SFT,
|
35 |
+
"TheBloke/airoboros-13B-HF": ModelType.SFT,
|
36 |
+
"TheBloke/koala-13B-HF": ModelType.SFT,
|
37 |
+
"TheBloke/Wizard-Vicuna-7B-Uncensored-HF": ModelType.SFT,
|
38 |
"TheBloke/dromedary-65b-lora-HF": ModelType.SFT,
|
39 |
+
"TheBloke/wizardLM-13B-1.0-fp16": ModelType.SFT,
|
40 |
+
"TheBloke/Wizard-Vicuna-30B-Uncensored-fp16": ModelType.SFT,
|
41 |
+
"TheBloke/wizard-vicuna-13B-HF": ModelType.SFT,
|
42 |
+
"TheBloke/UltraLM-13B-fp16": ModelType.SFT,
|
43 |
+
"TheBloke/OpenAssistant-SFT-7-Llama-30B-HF": ModelType.SFT,
|
44 |
"TheBloke/vicuna-13B-1.1-HF": ModelType.SFT,
|
45 |
+
"TheBloke/guanaco-13B-HF": ModelType.SFT,
|
46 |
+
"TheBloke/airoboros-7b-gpt4-fp16": ModelType.SFT,
|
47 |
+
"TheBloke/Llama-2-13B-fp16": ModelType.PT,
|
48 |
+
"TheBloke/Planner-7B-fp16": ModelType.SFT,
|
49 |
"TheBloke/Wizard-Vicuna-13B-Uncensored-HF": ModelType.SFT,
|
50 |
+
"TheBloke/gpt4-alpaca-lora-13B-HF": ModelType.SFT,
|
51 |
+
"TheBloke/gpt4-x-vicuna-13B-HF": ModelType.SFT,
|
52 |
+
"TheBloke/tulu-13B-fp16": ModelType.SFT,
|
53 |
+
"jphme/orca_mini_v2_ger_7b": ModelType.SFT,
|
54 |
+
"Ejafa/vicuna_7B_vanilla_1.1": ModelType.SFT,
|
55 |
+
"kevinpro/Vicuna-13B-CoT": ModelType.SFT,
|
56 |
+
"AlekseyKorshuk/pygmalion-6b-vicuna-chatml": ModelType.SFT,
|
57 |
"AlekseyKorshuk/chatml-pyg-v1": ModelType.SFT,
|
58 |
+
"concedo/Vicuzard-30B-Uncensored": ModelType.SFT,
|
59 |
"concedo/OPT-19M-ChatSalad": ModelType.SFT,
|
60 |
+
"concedo/Pythia-70M-ChatSalad": ModelType.SFT,
|
61 |
+
"digitous/13B-HyperMantis": ModelType.SFT,
|
62 |
+
"digitous/Adventien-GPTJ": ModelType.SFT,
|
63 |
+
"digitous/Alpacino13b": ModelType.SFT,
|
64 |
+
"digitous/GPT-R": ModelType.SFT,
|
65 |
+
"digitous/Javelin-R": ModelType.SFT,
|
66 |
+
"digitous/Javalion-GPTJ": ModelType.SFT,
|
67 |
"digitous/Javalion-R": ModelType.SFT,
|
68 |
+
"digitous/Skegma-GPTJ": ModelType.SFT,
|
69 |
"digitous/Alpacino30b": ModelType.SFT,
|
70 |
+
"digitous/Janin-GPTJ": ModelType.SFT,
|
71 |
+
"digitous/Janin-R": ModelType.SFT,
|
72 |
"digitous/Javelin-GPTJ": ModelType.SFT,
|
73 |
+
"SaylorTwift/gpt2_test": ModelType.PT,
|
74 |
"anton-l/gpt-j-tiny-random": ModelType.SFT,
|
75 |
+
"Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca": ModelType.SFT,
|
76 |
+
"Lazycuber/pyg-instruct-wizardlm": ModelType.SFT,
|
77 |
+
"Lazycuber/Janemalion-6B": ModelType.SFT,
|
78 |
"IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1": ModelType.SFT,
|
79 |
+
"IDEA-CCNL/Ziya-LLaMA-13B-v1": ModelType.SFT,
|
80 |
+
"dsvv-cair/alpaca-cleaned-llama-30b-bf16": ModelType.SFT,
|
81 |
"gpt2-medium": ModelType.PT,
|
82 |
+
"camel-ai/CAMEL-13B-Combined-Data": ModelType.SFT,
|
83 |
+
"camel-ai/CAMEL-13B-Role-Playing-Data": ModelType.SFT,
|
84 |
"PygmalionAI/pygmalion-6b": ModelType.SFT,
|
85 |
+
"PygmalionAI/metharme-1.3b": ModelType.SFT,
|
86 |
+
"PygmalionAI/pygmalion-1.3b": ModelType.SFT,
|
87 |
+
"PygmalionAI/pygmalion-350m": ModelType.SFT,
|
88 |
+
"PygmalionAI/pygmalion-2.7b": ModelType.SFT,
|
89 |
"medalpaca/medalpaca-7b": ModelType.SFT,
|
90 |
+
"lilloukas/Platypus-30B": ModelType.SFT,
|
91 |
+
"lilloukas/GPlatty-30B": ModelType.SFT,
|
92 |
+
"mncai/chatdoctor": ModelType.SFT,
|
93 |
+
"chaoyi-wu/MedLLaMA_13B": ModelType.SFT,
|
94 |
+
"LoupGarou/WizardCoder-Guanaco-15B-V1.0": ModelType.SFT,
|
95 |
+
"LoupGarou/WizardCoder-Guanaco-15B-V1.1": ModelType.SFT,
|
96 |
+
"hakurei/instruct-12b": ModelType.SFT,
|
97 |
"hakurei/lotus-12B": ModelType.SFT,
|
|
|
98 |
"shibing624/chinese-llama-plus-13b-hf": ModelType.SFT,
|
99 |
+
"shibing624/chinese-alpaca-plus-7b-hf": ModelType.SFT,
|
100 |
+
"shibing624/chinese-alpaca-plus-13b-hf": ModelType.SFT,
|
101 |
+
"mosaicml/mpt-7b-instruct": ModelType.SFT,
|
102 |
+
"mosaicml/mpt-30b-chat": ModelType.SFT,
|
103 |
+
"mosaicml/mpt-7b-storywriter": ModelType.SFT,
|
104 |
+
"mosaicml/mpt-30b-instruct": ModelType.SFT,
|
105 |
+
"mosaicml/mpt-7b-chat": ModelType.SFT,
|
106 |
+
"mosaicml/mpt-30b": ModelType.PT,
|
107 |
+
"Corianas/111m": ModelType.SFT,
|
108 |
+
"Corianas/Quokka_1.3b": ModelType.SFT,
|
109 |
+
"Corianas/256_5epoch": ModelType.SFT,
|
110 |
+
"Corianas/Quokka_256m": ModelType.SFT,
|
111 |
+
"Corianas/Quokka_590m": ModelType.SFT,
|
112 |
+
"Corianas/gpt-j-6B-Dolly": ModelType.SFT,
|
113 |
+
"Corianas/Quokka_2.7b": ModelType.SFT,
|
114 |
+
"cyberagent/open-calm-7b": ModelType.SFT,
|
115 |
+
"Aspik101/Nous-Hermes-13b-pl-lora_unload": ModelType.SFT,
|
116 |
+
"THUDM/chatglm2-6b": ModelType.SFT,
|
117 |
"MetaIX/GPT4-X-Alpasta-30b": ModelType.SFT,
|
118 |
+
"NYTK/PULI-GPTrio": ModelType.PT,
|
119 |
+
"EleutherAI/pythia-1.3b": ModelType.PT,
|
120 |
+
"EleutherAI/pythia-2.8b-deduped": ModelType.PT,
|
121 |
+
"EleutherAI/gpt-neo-125m": ModelType.PT,
|
122 |
+
"EleutherAI/pythia-160m": ModelType.PT,
|
123 |
+
"EleutherAI/gpt-neo-2.7B": ModelType.PT,
|
124 |
+
"EleutherAI/pythia-1b-deduped": ModelType.PT,
|
125 |
+
"EleutherAI/pythia-6.7b": ModelType.PT,
|
126 |
+
"EleutherAI/pythia-70m-deduped": ModelType.PT,
|
127 |
"EleutherAI/gpt-neox-20b": ModelType.PT,
|
128 |
+
"EleutherAI/pythia-1.4b-deduped": ModelType.PT,
|
129 |
+
"EleutherAI/pythia-2.7b": ModelType.PT,
|
130 |
+
"EleutherAI/pythia-6.9b-deduped": ModelType.PT,
|
131 |
+
"EleutherAI/pythia-70m": ModelType.PT,
|
132 |
"EleutherAI/gpt-j-6b": ModelType.PT,
|
133 |
+
"EleutherAI/pythia-12b-deduped": ModelType.PT,
|
134 |
+
"EleutherAI/gpt-neo-1.3B": ModelType.PT,
|
135 |
+
"EleutherAI/pythia-410m-deduped": ModelType.PT,
|
136 |
+
"EleutherAI/pythia-160m-deduped": ModelType.PT,
|
137 |
+
"EleutherAI/polyglot-ko-12.8b": ModelType.PT,
|
138 |
+
"EleutherAI/pythia-12b": ModelType.PT,
|
139 |
+
"roneneldan/TinyStories-33M": ModelType.PT,
|
140 |
+
"roneneldan/TinyStories-28M": ModelType.PT,
|
141 |
+
"roneneldan/TinyStories-1M": ModelType.PT,
|
142 |
+
"roneneldan/TinyStories-8M": ModelType.PT,
|
143 |
+
"roneneldan/TinyStories-3M": ModelType.PT,
|
144 |
+
"jerryjalapeno/nart-100k-7b": ModelType.SFT,
|
145 |
+
"lmsys/vicuna-13b-v1.3": ModelType.SFT,
|
146 |
+
"lmsys/vicuna-7b-v1.3": ModelType.SFT,
|
147 |
+
"lmsys/vicuna-13b-v1.1": ModelType.SFT,
|
148 |
"lmsys/vicuna-13b-delta-v1.1": ModelType.SFT,
|
149 |
"lmsys/vicuna-7b-delta-v1.1": ModelType.SFT,
|
150 |
"abhiramtirumala/DialoGPT-sarcastic-medium": ModelType.SFT,
|
151 |
+
"haonan-li/bactrian-x-llama-13b-merged": ModelType.SFT,
|
152 |
+
"Gryphe/MythoLogic-13b": ModelType.SFT,
|
153 |
+
"Gryphe/MythoBoros-13b": ModelType.SFT,
|
154 |
"pillowtalks-ai/delta13b": ModelType.SFT,
|
155 |
+
"wannaphong/openthaigpt-0.1.0-beta-full-model_for_open_llm_leaderboard": ModelType.SFT,
|
156 |
+
"bigcode/tiny_starcoder_py": ModelType.PT,
|
157 |
"bigcode/starcoderplus": ModelType.SFT,
|
158 |
+
"bigcode/gpt_bigcode-santacoder": ModelType.PT,
|
159 |
+
"bigcode/starcoder": ModelType.PT,
|
160 |
+
"Open-Orca/OpenOrca-Preview1-13B": ModelType.SFT,
|
161 |
"microsoft/DialoGPT-large": ModelType.SFT,
|
162 |
+
"microsoft/DialoGPT-small": ModelType.SFT,
|
163 |
+
"microsoft/DialoGPT-medium": ModelType.SFT,
|
164 |
"microsoft/CodeGPT-small-py": ModelType.SFT,
|
165 |
+
"Tincando/fiction_story_generator": ModelType.SFT,
|
166 |
"Pirr/pythia-13b-deduped-green_devil": ModelType.SFT,
|
167 |
"Aeala/GPT4-x-AlpacaDente2-30b": ModelType.SFT,
|
168 |
+
"Aeala/GPT4-x-AlpacaDente-30b": ModelType.SFT,
|
169 |
+
"Aeala/GPT4-x-Alpasta-13b": ModelType.SFT,
|
170 |
"Aeala/VicUnlocked-alpaca-30b": ModelType.SFT,
|
171 |
+
"Tap-M/Luna-AI-Llama2-Uncensored": ModelType.SFT,
|
172 |
+
"illuin/test-custom-llama": ModelType.SFT,
|
173 |
+
"dvruette/oasst-llama-13b-2-epochs": ModelType.SFT,
|
174 |
"dvruette/oasst-gpt-neox-20b-1000-steps": ModelType.SFT,
|
175 |
+
"dvruette/llama-13b-pretrained-dropout": ModelType.PT,
|
176 |
+
"dvruette/llama-13b-pretrained": ModelType.PT,
|
177 |
+
"dvruette/llama-13b-pretrained-sft-epoch-1": ModelType.PT,
|
178 |
+
"dvruette/llama-13b-pretrained-sft-do2": ModelType.PT,
|
179 |
+
"dvruette/oasst-gpt-neox-20b-3000-steps": ModelType.SFT,
|
180 |
+
"dvruette/oasst-pythia-12b-pretrained-sft": ModelType.PT,
|
181 |
+
"dvruette/oasst-pythia-6.9b-4000-steps": ModelType.SFT,
|
182 |
+
"dvruette/gpt-neox-20b-full-precision": ModelType.SFT,
|
183 |
+
"dvruette/oasst-llama-13b-1000-steps": ModelType.SFT,
|
184 |
"openlm-research/open_llama_7b_700bt_preview": ModelType.PT,
|
185 |
"openlm-research/open_llama_7b": ModelType.PT,
|
186 |
+
"openlm-research/open_llama_7b_v2": ModelType.PT,
|
187 |
"openlm-research/open_llama_3b": ModelType.PT,
|
188 |
+
"openlm-research/open_llama_13b": ModelType.PT,
|
189 |
+
"openlm-research/open_llama_3b_v2": ModelType.PT,
|
190 |
"PocketDoc/Dans-PileOfSets-Mk1-llama-13b-merged": ModelType.SFT,
|
191 |
+
"GeorgiaTechResearchInstitute/galpaca-30b": ModelType.SFT,
|
192 |
+
"GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct": ModelType.SFT,
|
193 |
"databricks/dolly-v2-7b": ModelType.SFT,
|
194 |
"databricks/dolly-v2-3b": ModelType.SFT,
|
195 |
"databricks/dolly-v2-12b": ModelType.SFT,
|
|
|
196 |
"Rachneet/gpt2-xl-alpaca": ModelType.SFT,
|
197 |
"Locutusque/gpt2-conversational-or-qa": ModelType.SFT,
|
198 |
+
"psyche/kogpt": ModelType.SFT,
|
199 |
"NbAiLab/nb-gpt-j-6B-alpaca": ModelType.SFT,
|
200 |
+
"Mikael110/llama-2-7b-guanaco-fp16": ModelType.SFT,
|
201 |
+
"Mikael110/llama-2-13b-guanaco-fp16": ModelType.SFT,
|
202 |
+
"Fredithefish/CrimsonPajama": ModelType.SFT,
|
203 |
+
"Fredithefish/RedPajama-INCITE-Chat-3B-ShareGPT-11K": ModelType.SFT,
|
204 |
"Fredithefish/ScarletPajama-3B-HF": ModelType.SFT,
|
205 |
+
"Fredithefish/RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4": ModelType.SFT,
|
206 |
+
"eachadea/vicuna-13b-1.1": ModelType.SFT,
|
207 |
"eachadea/vicuna-7b-1.1": ModelType.SFT,
|
208 |
"eachadea/vicuna-13b": ModelType.SFT,
|
209 |
"openaccess-ai-collective/wizard-mega-13b": ModelType.SFT,
|
210 |
"openaccess-ai-collective/manticore-13b": ModelType.SFT,
|
211 |
"openaccess-ai-collective/manticore-30b-chat-pyg-alpha": ModelType.SFT,
|
212 |
"openaccess-ai-collective/minotaur-13b": ModelType.SFT,
|
213 |
+
"openaccess-ai-collective/minotaur-13b-fixed": ModelType.SFT,
|
214 |
+
"openaccess-ai-collective/hippogriff-30b-chat": ModelType.SFT,
|
215 |
+
"openaccess-ai-collective/manticore-13b-chat-pyg": ModelType.SFT,
|
216 |
"pythainlp/wangchanglm-7.5B-sft-enth": ModelType.SFT,
|
217 |
"pythainlp/wangchanglm-7.5B-sft-en-sharded": ModelType.SFT,
|
218 |
+
"euclaise/gpt-neox-122m-minipile-digits": ModelType.SFT,
|
219 |
+
"stabilityai/FreeWilly1-Delta-SafeTensor": ModelType.SFT,
|
220 |
"stabilityai/stablelm-tuned-alpha-7b": ModelType.SFT,
|
221 |
+
"stabilityai/FreeWilly2": ModelType.SFT,
|
222 |
+
"stabilityai/stablelm-base-alpha-7b": ModelType.PT,
|
223 |
+
"stabilityai/stablelm-base-alpha-3b": ModelType.PT,
|
224 |
+
"stabilityai/stablelm-tuned-alpha-3b": ModelType.SFT,
|
225 |
+
"alibidaran/medical_transcription_generator": ModelType.SFT,
|
226 |
"CalderaAI/30B-Lazarus": ModelType.SFT,
|
227 |
+
"CalderaAI/13B-BlueMethod": ModelType.SFT,
|
228 |
+
"CalderaAI/13B-Ouroboros": ModelType.SFT,
|
229 |
+
"KoboldAI/OPT-13B-Erebus": ModelType.SFT,
|
230 |
+
"KoboldAI/GPT-J-6B-Janeway": ModelType.SFT,
|
231 |
+
"KoboldAI/GPT-J-6B-Shinen": ModelType.SFT,
|
232 |
+
"KoboldAI/fairseq-dense-2.7B": ModelType.PT,
|
233 |
+
"KoboldAI/OPT-6B-nerys-v2": ModelType.SFT,
|
234 |
+
"KoboldAI/GPT-NeoX-20B-Skein": ModelType.SFT,
|
235 |
+
"KoboldAI/PPO_Pygway-6b-Mix": ModelType.SFT,
|
236 |
+
"KoboldAI/fairseq-dense-6.7B": ModelType.PT,
|
237 |
+
"KoboldAI/fairseq-dense-125M": ModelType.PT,
|
238 |
"KoboldAI/OPT-13B-Nerybus-Mix": ModelType.SFT,
|
239 |
+
"KoboldAI/OPT-2.7B-Erebus": ModelType.SFT,
|
240 |
+
"KoboldAI/OPT-350M-Nerys-v2": ModelType.SFT,
|
241 |
+
"KoboldAI/OPT-2.7B-Nerys-v2": ModelType.SFT,
|
242 |
+
"KoboldAI/OPT-2.7B-Nerybus-Mix": ModelType.SFT,
|
243 |
+
"KoboldAI/OPT-13B-Nerys-v2": ModelType.SFT,
|
244 |
+
"KoboldAI/GPT-NeoX-20B-Erebus": ModelType.SFT,
|
245 |
+
"KoboldAI/OPT-6.7B-Erebus": ModelType.SFT,
|
246 |
+
"KoboldAI/fairseq-dense-355M": ModelType.PT,
|
247 |
+
"KoboldAI/OPT-6.7B-Nerybus-Mix": ModelType.SFT,
|
248 |
+
"KoboldAI/GPT-J-6B-Adventure": ModelType.SFT,
|
249 |
+
"KoboldAI/OPT-350M-Erebus": ModelType.SFT,
|
250 |
+
"KoboldAI/GPT-J-6B-Skein": ModelType.SFT,
|
251 |
+
"KoboldAI/OPT-30B-Erebus": ModelType.SFT,
|
252 |
+
"klosax/pythia-160m-deduped-step92k-193bt": ModelType.PT,
|
253 |
+
"klosax/open_llama_3b_350bt_preview": ModelType.PT,
|
254 |
+
"klosax/openllama-3b-350bt": ModelType.PT,
|
255 |
+
"klosax/pythia-70m-deduped-step44k-92bt": ModelType.PT,
|
256 |
+
"klosax/open_llama_13b_600bt_preview": ModelType.PT,
|
257 |
+
"klosax/open_llama_7b_400bt_preview": ModelType.PT,
|
258 |
+
"WeOpenML/Alpaca-7B-v1": ModelType.SFT,
|
259 |
+
"WeOpenML/PandaLM-Alpaca-7B-v1": ModelType.SFT,
|
260 |
+
"TFLai/gpt2-turkish-uncased": ModelType.SFT,
|
261 |
+
"ehartford/WizardLM-13B-Uncensored": ModelType.SFT,
|
262 |
+
"ehartford/dolphin-llama-13b": ModelType.SFT,
|
263 |
+
"ehartford/Wizard-Vicuna-30B-Uncensored": ModelType.SFT,
|
264 |
+
"ehartford/WizardLM-30B-Uncensored": ModelType.SFT,
|
265 |
+
"ehartford/Wizard-Vicuna-13B-Uncensored": ModelType.SFT,
|
266 |
+
"ehartford/WizardLM-7B-Uncensored": ModelType.SFT,
|
267 |
+
"ehartford/based-30b": ModelType.SFT,
|
268 |
+
"ehartford/Wizard-Vicuna-7B-Uncensored": ModelType.SFT,
|
269 |
"wahaha1987/llama_7b_sharegpt94k_fastchat": ModelType.SFT,
|
270 |
+
"wahaha1987/llama_13b_sharegpt94k_fastchat": ModelType.SFT,
|
271 |
+
"OpenAssistant/oasst-sft-1-pythia-12b": ModelType.SFT,
|
272 |
+
"OpenAssistant/stablelm-7b-sft-v7-epoch-3": ModelType.SFT,
|
273 |
"OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5": ModelType.SFT,
|
274 |
+
"OpenAssistant/pythia-12b-sft-v8-2.5k-steps": ModelType.SFT,
|
275 |
+
"OpenAssistant/pythia-12b-sft-v8-7k-steps": ModelType.SFT,
|
276 |
+
"OpenAssistant/pythia-12b-pre-v8-12.5k-steps": ModelType.SFT,
|
277 |
"junelee/wizard-vicuna-13b": ModelType.SFT,
|
278 |
+
"BreadAi/gpt-YA-1-1_160M": ModelType.PT,
|
279 |
+
"BreadAi/MuseCan": ModelType.PT,
|
280 |
+
"BreadAi/MusePy-1-2": ModelType.PT,
|
281 |
+
"BreadAi/DiscordPy": ModelType.PT,
|
282 |
+
"BreadAi/PM_modelV2": ModelType.PT,
|
283 |
+
"BreadAi/gpt-Youtube": ModelType.PT,
|
284 |
"BreadAi/StoryPy": ModelType.SFT,
|
285 |
+
"julianweng/Llama-2-7b-chat-orcah": ModelType.SFT,
|
286 |
+
"AGI-inc/lora_moe_7b_baseline": ModelType.SFT,
|
287 |
+
"AGI-inc/lora_moe_7b": ModelType.SFT,
|
288 |
+
"togethercomputer/GPT-NeoXT-Chat-Base-20B": ModelType.SFT,
|
289 |
+
"togethercomputer/RedPajama-INCITE-Chat-7B-v0.1": ModelType.SFT,
|
290 |
+
"togethercomputer/RedPajama-INCITE-Instruct-7B-v0.1": ModelType.SFT,
|
291 |
+
"togethercomputer/RedPajama-INCITE-7B-Base": ModelType.PT,
|
292 |
+
"togethercomputer/RedPajama-INCITE-7B-Instruct": ModelType.SFT,
|
293 |
"togethercomputer/RedPajama-INCITE-Base-3B-v1": ModelType.PT,
|
294 |
+
"togethercomputer/Pythia-Chat-Base-7B": ModelType.SFT,
|
295 |
"togethercomputer/RedPajama-INCITE-Base-7B-v0.1": ModelType.PT,
|
296 |
+
"togethercomputer/GPT-JT-6B-v1": ModelType.SFT,
|
297 |
+
"togethercomputer/GPT-JT-6B-v0": ModelType.SFT,
|
298 |
+
"togethercomputer/RedPajama-INCITE-Chat-3B-v1": ModelType.SFT,
|
299 |
+
"togethercomputer/RedPajama-INCITE-7B-Chat": ModelType.SFT,
|
300 |
+
"togethercomputer/RedPajama-INCITE-Instruct-3B-v1": ModelType.SFT,
|
301 |
"Writer/camel-5b-hf": ModelType.SFT,
|
302 |
"Writer/palmyra-base": ModelType.PT,
|
303 |
+
"MBZUAI/LaMini-GPT-1.5B": ModelType.SFT,
|
304 |
+
"MBZUAI/lamini-cerebras-111m": ModelType.SFT,
|
305 |
+
"MBZUAI/lamini-neo-1.3b": ModelType.SFT,
|
306 |
+
"MBZUAI/lamini-cerebras-1.3b": ModelType.SFT,
|
307 |
+
"MBZUAI/lamini-cerebras-256m": ModelType.SFT,
|
308 |
+
"MBZUAI/LaMini-GPT-124M": ModelType.SFT,
|
309 |
"MBZUAI/lamini-neo-125m": ModelType.SFT,
|
310 |
+
"TehVenom/DiffMerge-DollyGPT-Pygmalion": ModelType.SFT,
|
311 |
+
"TehVenom/PPO_Shygmalion-6b": ModelType.SFT,
|
312 |
+
"TehVenom/Dolly_Shygmalion-6b-Dev_V8P2": ModelType.SFT,
|
313 |
+
"TehVenom/Pygmalion_AlpacaLora-7b": ModelType.SFT,
|
314 |
+
"TehVenom/PPO_Pygway-V8p4_Dev-6b": ModelType.SFT,
|
315 |
+
"TehVenom/Dolly_Malion-6b": ModelType.SFT,
|
316 |
+
"TehVenom/PPO_Shygmalion-V8p4_Dev-6b": ModelType.SFT,
|
317 |
+
"TehVenom/ChanMalion": ModelType.SFT,
|
318 |
+
"TehVenom/GPT-J-Pyg_PPO-6B": ModelType.SFT,
|
319 |
+
"TehVenom/Pygmalion-13b-Merged": ModelType.SFT,
|
320 |
+
"TehVenom/Metharme-13b-Merged": ModelType.SFT,
|
321 |
+
"TehVenom/Dolly_Shygmalion-6b": ModelType.SFT,
|
322 |
+
"TehVenom/GPT-J-Pyg_PPO-6B-Dev-V8p4": ModelType.SFT,
|
323 |
+
"georgesung/llama2_7b_chat_uncensored": ModelType.SFT,
|
324 |
+
"vicgalle/gpt2-alpaca": ModelType.SFT,
|
325 |
+
"vicgalle/alpaca-7b": ModelType.SFT,
|
326 |
"vicgalle/gpt2-alpaca-gpt4": ModelType.SFT,
|
327 |
"facebook/opt-350m": ModelType.PT,
|
328 |
"facebook/opt-125m": ModelType.PT,
|
329 |
+
"facebook/xglm-4.5B": ModelType.PT,
|
330 |
+
"facebook/opt-2.7b": ModelType.PT,
|
331 |
+
"facebook/opt-6.7b": ModelType.PT,
|
332 |
+
"facebook/galactica-30b": ModelType.PT,
|
333 |
"facebook/opt-13b": ModelType.PT,
|
|
|
334 |
"facebook/opt-66b": ModelType.PT,
|
335 |
+
"facebook/xglm-7.5B": ModelType.PT,
|
336 |
+
"facebook/xglm-564M": ModelType.PT,
|
337 |
+
"facebook/opt-30b": ModelType.PT,
|
338 |
+
"golaxy/gogpt-7b": ModelType.SFT,
|
339 |
+
"psmathur/orca_mini_v2_7b": ModelType.SFT,
|
340 |
+
"psmathur/orca_mini_7b": ModelType.SFT,
|
341 |
+
"psmathur/orca_mini_3b": ModelType.SFT,
|
342 |
+
"psmathur/orca_mini_v2_13b": ModelType.SFT,
|
343 |
"gpt2-xl": ModelType.PT,
|
344 |
+
"lxe/Cerebras-GPT-2.7B-Alpaca-SP": ModelType.SFT,
|
345 |
+
"Monero/Manticore-13b-Chat-Pyg-Guanaco": ModelType.SFT,
|
346 |
+
"Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b": ModelType.SFT,
|
347 |
+
"Monero/WizardLM-13b-OpenAssistant-Uncensored": ModelType.SFT,
|
348 |
+
"Monero/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b": ModelType.SFT,
|
349 |
+
"jzjiao/opt-1.3b-rlhf": ModelType.SFT,
|
350 |
"HuggingFaceH4/starchat-beta": ModelType.SFT,
|
351 |
+
"KnutJaegersberg/gpt-2-xl-EvolInstruct": ModelType.SFT,
|
352 |
+
"KnutJaegersberg/megatron-GPT-2-345m-EvolInstruct": ModelType.SFT,
|
353 |
+
"openchat/openchat_8192": ModelType.SFT,
|
354 |
+
"openchat/openchat_v2": ModelType.SFT,
|
355 |
+
"openchat/openchat_v2_w": ModelType.SFT,
|
356 |
"ausboss/llama-13b-supercot": ModelType.SFT,
|
357 |
"ausboss/llama-30b-supercot": ModelType.SFT,
|
358 |
"Neko-Institute-of-Science/metharme-7b": ModelType.SFT,
|
359 |
+
"Neko-Institute-of-Science/pygmalion-7b": ModelType.SFT,
|
360 |
"SebastianSchramm/Cerebras-GPT-111M-instruction": ModelType.SFT,
|
361 |
"victor123/WizardLM-13B-1.0": ModelType.SFT,
|
362 |
+
"OpenBuddy/openbuddy-openllama-13b-v7-fp16": ModelType.SFT,
|
363 |
+
"baichuan-inc/Baichuan-7B": ModelType.PT,
|
364 |
"tiiuae/falcon-40b-instruct": ModelType.SFT,
|
365 |
"tiiuae/falcon-40b": ModelType.PT,
|
366 |
"tiiuae/falcon-7b": ModelType.PT,
|
367 |
+
"YeungNLP/firefly-llama-13b": ModelType.SFT,
|
368 |
+
"YeungNLP/firefly-llama-13b-v1.2": ModelType.SFT,
|
369 |
+
"YeungNLP/firefly-ziya-13b": ModelType.SFT,
|
370 |
+
"shaohang/Sparse0.5_OPT-1.3": ModelType.SFT,
|
371 |
+
"xzuyModelType.lpacino-SuperCOT-13B": ModelType.SFT,
|
372 |
"xzuyn/MedicWizard-7B": ModelType.SFT,
|
373 |
"beomi/KoAlpaca-Polyglot-5.8B": ModelType.SFT,
|
374 |
+
"beomi/llama-2-ko-7b": ModelType.SFT,
|
375 |
+
"Salesforce/codegen-6B-multi": ModelType.PT,
|
376 |
"Salesforce/codegen-16B-nl": ModelType.PT,
|
377 |
+
"Salesforce/codegen-6B-nl": ModelType.PT,
|
378 |
"ai-forever/rugpt3large_based_on_gpt2": ModelType.SFT,
|
379 |
"gpt2-large": ModelType.PT,
|
380 |
+
"frank098/orca_mini_3b_juniper": ModelType.SFT,
|
381 |
+
"frank098/WizardLM_13B_juniper": ModelType.SFT,
|
382 |
"huggingface/llama-13b": ModelType.PT,
|
383 |
"huggingface/llama-7b": ModelType.PT,
|
384 |
"huggingface/llama-65b": ModelType.PT,
|
385 |
+
"huggingface/llama-65b": ModelType.PT,
|
386 |
"huggingface/llama-30b": ModelType.PT,
|
387 |
+
"jondurbiModelType.iroboros-13b-gpt4-1.4": ModelType.SFT,
|
388 |
+
"jondurbiModelType.iroboros-7b": ModelType.SFT,
|
389 |
+
"jondurbiModelType.iroboros-7b-gpt4-1.4": ModelType.SFT,
|
390 |
+
"jondurbiModelType.iroboros-l2-13b-gpt4-1.4.1": ModelType.SFT,
|
391 |
+
"jondurbiModelType.iroboros-13b": ModelType.SFT,
|
392 |
+
"ariellee/SuperPlatty-30B": ModelType.SFT,
|
393 |
+
"danielhanchen/open_llama_3b_600bt_preview": ModelType.SFT,
|
394 |
+
"cerebras/Cerebras-GPT-256M": ModelType.PT,
|
395 |
"cerebras/Cerebras-GPT-1.3B": ModelType.PT,
|
396 |
+
"cerebras/Cerebras-GPT-13B": ModelType.PT,
|
397 |
+
"cerebras/Cerebras-GPT-2.7B": ModelType.PT,
|
398 |
"cerebras/Cerebras-GPT-111M": ModelType.PT,
|
399 |
+
"cerebras/Cerebras-GPT-6.7B": ModelType.PT,
|
400 |
+
"Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-hf": ModelType.RL,
|
401 |
+
"Yhyu13/llama-30B-hf-openassitant": ModelType.SFT,
|
402 |
+
"NousResearch/Nous-Hermes-Llama2-13b": ModelType.SFT,
|
403 |
+
"NousResearch/Redmond-Puffin-13B": ModelType.SFT,
|
404 |
"NousResearch/Nous-Hermes-13b": ModelType.SFT,
|
405 |
"project-baize/baize-v2-7b": ModelType.SFT,
|
406 |
"project-baize/baize-v2-13b": ModelType.SFT,
|
407 |
+
"LLMs/WizardLM-13B-V1.0": ModelType.SFT,
|
408 |
"LLMs/AlpacaGPT4-7B-elina": ModelType.SFT,
|
409 |
+
"wenge-research/yayi-7b-llama2": ModelType.SFT,
|
410 |
+
"yhyhy3/open_llama_7b_v2_med_instruct": ModelType.SFT,
|
411 |
+
"llama-anon/instruct-13b": ModelType.SFT,
|
412 |
"huggingtweets/jerma985": ModelType.SFT,
|
413 |
+
"huggingtweets/gladosystem": ModelType.SFT,
|
414 |
+
"huggingtweets/bladeecity-jerma985": ModelType.SFT,
|
415 |
+
"huggyllama/llama-13b": ModelType.PT,
|
416 |
"huggyllama/llama-65b": ModelType.PT,
|
417 |
+
"FabbriSimo01/Facebook_opt_1.3b_Quantized": ModelType.PT,
|
418 |
+
"upstage/llama-30b-instruct-2048": ModelType.SFT,
|
419 |
+
"upstage/llama-30b-instruct": ModelType.SFT,
|
420 |
"WizardLM/WizardLM-13B-1.0": ModelType.SFT,
|
421 |
+
"WizardLM/WizardLM-30B-V1.0": ModelType.SFT,
|
422 |
+
"WizardLM/WizardCoder-15B-V1.0": ModelType.SFT,
|
423 |
"gpt2": ModelType.PT,
|
424 |
+
"keyfan/vicuna-chinese-replication-v1.1": ModelType.SFT,
|
425 |
+
"nthngdy/pythia-owt2-70m-100k": ModelType.SFT,
|
426 |
+
"nthngdy/pythia-owt2-70m-50k": ModelType.SFT,
|
427 |
+
"quantumaikr/KoreanLM-hf": ModelType.SFT,
|
428 |
+
"quantumaikr/open_llama_7b_hf": ModelType.SFT,
|
429 |
"MayaPH/FinOPT-Lincoln": ModelType.SFT,
|
430 |
"MayaPH/FinOPT-Franklin": ModelType.SFT,
|
431 |
+
"MayaPH/GodziLLa-30B": ModelType.SFT,
|
432 |
+
"MayaPH/FinOPT-Washington": ModelType.SFT,
|
433 |
+
"ogimgio/gpt-neo-125m-neurallinguisticpioneers": ModelType.SFT,
|
434 |
+
"layoric/llama-2-13b-code-alpaca": ModelType.SFT,
|
435 |
+
"CobraMamba/mamba-gpt-3b": ModelType.SFT,
|
436 |
"timdettmers/guanaco-33b-merged": ModelType.SFT,
|
|
|
|
|
437 |
"elinas/chronos-33b": ModelType.SFT,
|
438 |
+
"heegyu/RedTulu-Uncensored-3B-0719": ModelType.SFT,
|
439 |
+
"heegyu/WizardVicuna-Uncensored-3B-0719": ModelType.SFT,
|
440 |
+
"heegyu/WizardVicuna-3B-0719": ModelType.SFT,
|
441 |
+
"meta-llama/Llama-2-7b-chat-hf": ModelType.RL,
|
442 |
+
"meta-llama/Llama-2-7b-hf": ModelType.PT,
|
443 |
+
"meta-llama/Llama-2-13b-chat-hf": ModelType.RL,
|
444 |
+
"meta-llama/Llama-2-13b-hf": ModelType.PT,
|
445 |
+
"meta-llama/Llama-2-70b-chat-hf": ModelType.RL,
|
446 |
+
"meta-llama/Llama-2-70b-hf": ModelType.PT,
|
447 |
"xhyi/PT_GPTNEO350_ATG": ModelType.SFT,
|
448 |
+
"h2oai/h2ogpt-gm-oasst1-en-1024-20b": ModelType.SFT,
|
449 |
+
"h2oai/h2ogpt-gm-oasst1-en-1024-open-llama-7b-preview-400bt": ModelType.SFT,
|
450 |
+
"h2oai/h2ogpt-oig-oasst1-512-6_9b": ModelType.SFT,
|
451 |
+
"h2oai/h2ogpt-oasst1-512-12b": ModelType.SFT,
|
452 |
+
"h2oai/h2ogpt-oig-oasst1-256-6_9b": ModelType.SFT,
|
453 |
+
"h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt": ModelType.SFT,
|
454 |
"h2oai/h2ogpt-oasst1-512-20b": ModelType.SFT,
|
455 |
+
"h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2": ModelType.SFT,
|
456 |
"h2oai/h2ogpt-gm-oasst1-en-1024-12b": ModelType.SFT,
|
457 |
+
"h2oai/h2ogpt-gm-oasst1-multilang-1024-20b": ModelType.SFT,
|
458 |
+
"bofenghuang/vigogne-13b-instruct": ModelType.SFT,
|
459 |
+
"Vmware/open-llama-7b-v2-open-instruct": ModelType.SFT,
|
460 |
+
"VMware/open-llama-0.7T-7B-open-instruct-v1.1": ModelType.SFT,
|
461 |
+
"ewof/koishi-instruct-3b": ModelType.SFT,
|
462 |
}
|
463 |
|
464 |
|