models.md
June 10, 2023 ยท View on GitHub
We support the following models
| Model | model_name | model_path |
|---|---|---|
| GPT-4 | openai | OpenAI |
| Palm 2 Instruct | ||
| ChatGPT | openai | OpenAI |
| LLaMA | llama | decapoda-research/llama-65b-hf |
| Alpaca Lora | llama | TheBloke/alpaca-lora-65B-GPTQ-4bit |
| GPT4 Alpaca Lora | llama | TheBloke/gpt4-alpaca-lora-30b-HF |
| OpenAssistant LLAMA | llama | TheBloke/OpenAssistant-SFT-7-Llama-30B-HF |
| LLaMA | llama | decapoda-research/llama-30b-hf |
| GPT4 Alpaca Lora GPTQ | llama | TheBloke/gpt4-alpaca-lora-30B-GPTQ-4bit-128g |
| Flan-UL2 | seq_to_seq | google/flan-ul2 |
| Flan UL2 Alpaca Lora | seq_to_seq | VMware/flan-ul2-alpaca-lora |
| Flan UL2 Dolly Lora | seq_to_seq | coniferlabs/flan-ul2-dolly-lora |
| OPT IML | causal | facebook/opt-iml-30b |
| OPT | causal | facebook/opt-30b |
| Flan-Alpaca | llama | declare-lab/flan-alpaca-xxl |
| Flan-T5-XXL | seq_to_seq | google/flan-t5-xxl/ |
| TK-Instruct | seq_to_seq | allenai/tk-instruct-11b-def-pos |
| T0 | seq_to_seq | bigscience/T0pp |
| StableVicuna | llama | TheBloke/stable-vicuna-13B-HF |
| Vicuna | llama | eachadea/vicuna-13b-1.1 |
| GPT4 Alpaca Lora | llama | TheBloke/gpt4-alpaca-lora-13B-HF |
| LLaMA | llama | decapoda-research/llama-13b-hf |
| Koala | llama | TheBloke/koala-13B-HF |
| Raven v11 | rwkv | BlinkDL/rwkv-4-raven |
| Dolly V2 | causal | databricks/dolly-v2-12b |
| StarCoder | causal | bigcode/starcoder |
| StarChat | causal | HuggingFaceH4/starchat-alpha |
| T5 XXL LM | seq_to_seq | google/t5-xxl-lm-adapt |
| Moon Base | causal | fnlp/moss-moon-003-base |
| Moon SFT | causal | fnlp/moss-moon-003-sft |
| WizardLM-13B-Uncensored | llama | ehartford/WizardLM-13B-Uncensored |
| Guanaco | llama | TheBloke/guanaco-13B-GGML |
| pythia | causal | EleutherAI/pythia-12b |
| GPT4 Alpaca Lora 7B | llama | chansung/gpt4-alpaca-lora-7b |
| Alpaca Lora 7B | llama | tloen/alpaca-lora-7b |
| Alpaca 7B | llama | chavinlo/alpaca-native |
| Mosaic-7B-Chat | causal | mosaicml/mpt-7b-chat |
| LLaMA | llama | decapoda-research/llama-7b-hf |
| StableLM Tuned | causal | stabilityai/stablelm-base-alpha-7b |
| Mosaic-7B | causal | mosaicml/mpt-7b |
| Mosaic-7B-Instruct | causal | mosaicml/mpt-7b-instruct |
| Raven-rwkv-7B | rwkv | spaces/BlinkDL/Raven-RWKV-7B |
| RWKV-pile-7B | rwkv | BlinkDL/rwkv-4-pile-7b |
| Flan-T5-XL | seq_to_seq | google/flan-t5-xl |
| CodeGen-6B-mono | causal | Salesforce/codegen-6B-mono |
| ChatGLM | chatglm | THUDM/chatglm-6b |
| RedPajama | causal | togethercomputer/RedPajama-INCITE-7B-Instruct |
| TK Instruct XL | seq_to_seq | allenai/tk-instruct-3b-def-pos |
| T5 XL LM | seq_to_seq | google/t5-xl-lm-adapt |
| Flan Alpaca XL | llama | declare-lab/flan-alpaca-xl |
| Falcon-7b | causal | tiiuae/falcon-7b |
| Falcon-7b-Instruct | causal | tiiuae/falcon-7b-instruct |
| TK Instruct Large | seq_to_seq | allenai/tk-instruct-large-def-pos |
| Flan T5 Large | seq_to_seq | google/flan-t5-large |
| T5 Large LM | seq_to_seq | google/t5-base-lm-adapt |
| Flan Alpaca Large | llama | declare-lab/flan-alpaca-large |
| TK Instruct Base | seq_to_seq | allenai/tk-instruct-base-def-pos |
| Flan T5 Base | seq_to_seq | google/flan-t5-base |
| T5 Base LM | seq_to_seq | google/t5-base-lm-adapt |
| Flan Alpaca Base | llama | declare-lab/flan-alpaca-base |