Skip to content

Commit

Permalink
Added new model to Together.ai
Browse files Browse the repository at this point in the history
  • Loading branch information
@davorrunje
davorrunje committed Jul 6, 2024
1 parent 5f32798 commit de83397
Show file tree
Hide file tree
Showing 2 changed files with 48 additions and 46 deletions.
93 changes: 47 additions & 46 deletions fastagency/models/llms/together.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,66 +14,66 @@

# retrieve the models from the API on June 26, 2024
together_model_string = {
"WizardLM v1.2 (13B)": "WizardLM/WizardLM-13B-V1.2",
"Code Llama Instruct (34B)": "togethercomputer/CodeLlama-34b-Instruct",
"Upstage SOLAR Instruct v1 (11B)": "upstage/SOLAR-10.7B-Instruct-v1.0",
"OpenHermes-2-Mistral (7B)": "teknium/OpenHermes-2-Mistral-7B",
"LLaMA-2-7B-32K-Instruct (7B)": "togethercomputer/Llama-2-7B-32K-Instruct",
"ReMM SLERP L2 (13B)": "Undi95/ReMM-SLERP-L2-13B",
"Toppy M (7B)": "Undi95/Toppy-M-7B",
"OpenChat 3.5": "openchat/openchat-3.5-1210",
"Chronos Hermes (13B)": "Austism/chronos-hermes-13b",
"MythoMax-L2 (13B)": "Gryphe/MythoMax-L2-13b",
"Nous Capybara v1.9 (7B)": "NousResearch/Nous-Capybara-7B-V1p9",
"Nous Hermes 2 - Mistral DPO (7B)": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
"Nous Hermes 2 - Mixtral 8x7B-DPO ": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"Nous Hermes 2 - Mixtral 8x7B-SFT": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
"Nous Hermes-2 Yi (34B)": "NousResearch/Nous-Hermes-2-Yi-34B",
"Nous Hermes Llama-2 (13B)": "NousResearch/Nous-Hermes-Llama2-13b",
"Nous Hermes LLaMA-2 (7B)": "NousResearch/Nous-Hermes-llama-2-7b",
"OpenOrca Mistral (7B) 8K": "Open-Orca/Mistral-7B-OpenOrca",
"Qwen 1.5 Chat (0.5B)": "Qwen/Qwen1.5-0.5B-Chat",
"Qwen 1.5 Chat (1.8B)": "Qwen/Qwen1.5-1.8B-Chat",
"Qwen 1.5 Chat (110B)": "Qwen/Qwen1.5-110B-Chat",
"Qwen 1.5 Chat (14B)": "Qwen/Qwen1.5-14B-Chat",
"Qwen 1.5 Chat (32B)": "Qwen/Qwen1.5-32B-Chat",
"Qwen 1.5 Chat (4B)": "Qwen/Qwen1.5-4B-Chat",
"Qwen 1.5 Chat (72B)": "Qwen/Qwen1.5-72B-Chat",
"Snorkel Mistral PairRM DPO (7B)": "snorkelai/Snorkel-Mistral-PairRM-DPO",
"Qwen 1.5 Chat (7B)": "Qwen/Qwen1.5-7B-Chat",
"Qwen 2 Instruct (72B)": "Qwen/Qwen2-72B-Instruct",
"Qwen 1.5 Chat (14B)": "Qwen/Qwen1.5-14B-Chat",
"Qwen 1.5 Chat (1.8B)": "Qwen/Qwen1.5-1.8B-Chat",
"Snowflake Arctic Instruct": "Snowflake/snowflake-arctic-instruct",
"ReMM SLERP L2 (13B)": "Undi95/ReMM-SLERP-L2-13B",
"Toppy M (7B)": "Undi95/Toppy-M-7B",
"WizardLM v1.2 (13B)": "WizardLM/WizardLM-13B-V1.2",
"OLMo Instruct (7B)": "allenai/OLMo-7B-Instruct",
"Code Llama Instruct (13B)": "togethercomputer/CodeLlama-13b-Instruct",
"Code Llama Instruct (34B)": "togethercomputer/CodeLlama-34b-Instruct",
"Code Llama Instruct (70B)": "codellama/CodeLlama-70b-Instruct-hf",
"Code Llama Instruct (7B)": "togethercomputer/CodeLlama-7b-Instruct",
"Nous Hermes 2 - Mixtral 8x7B-SFT": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
"Dolphin 2.5 Mixtral 8x7b": "cognitivecomputations/dolphin-2.5-mixtral-8x7b",
"DBRX Instruct": "databricks/dbrx-instruct",
"Nous Hermes 2 - Mixtral 8x7B-DPO ": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"Mixtral-8x22B Instruct v0.1": "mistralai/Mixtral-8x22B-Instruct-v0.1",
"Deepseek Coder Instruct (33B)": "deepseek-ai/deepseek-coder-33b-instruct",
"DeepSeek LLM Chat (67B)": "deepseek-ai/deepseek-llm-67b-chat",
"Nous Hermes Llama-2 (13B)": "NousResearch/Nous-Hermes-Llama2-13b",
"Vicuna v1.5 (13B)": "lmsys/vicuna-13b-v1.5",
"Qwen 1.5 Chat (0.5B)": "Qwen/Qwen1.5-0.5B-Chat",
"Code Llama Instruct (7B)": "togethercomputer/CodeLlama-7b-Instruct",
"Nous Hermes-2 Yi (34B)": "NousResearch/Nous-Hermes-2-Yi-34B",
"Code Llama Instruct (13B)": "togethercomputer/CodeLlama-13b-Instruct",
"Llama3 8B Chat HF INT4": "togethercomputer/Llama-3-8b-chat-hf-int4",
"OpenHermes-2.5-Mistral (7B)": "teknium/OpenHermes-2p5-Mistral-7B",
"Nous Capybara v1.9 (7B)": "NousResearch/Nous-Capybara-7B-V1p9",
"Nous Hermes 2 - Mistral DPO (7B)": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
"StripedHyena Nous (7B)": "togethercomputer/StripedHyena-Nous-7B",
"Alpaca (7B)": "togethercomputer/alpaca-7b",
"Platypus2 Instruct (70B)": "garage-bAInd/Platypus2-70B-instruct",
"Gemma Instruct (2B)": "google/gemma-2b-it",
"Gemma Instruct (7B)": "google/gemma-7b-it",
"Vicuna v1.5 (13B)": "lmsys/vicuna-13b-v1.5",
"Vicuna v1.5 (7B)": "lmsys/vicuna-7b-v1.5",
"Reserved - DBRX Instruct": "medaltv/dbrx-instruct",
"LLaMA-2 Chat (13B)": "togethercomputer/llama-2-13b-chat",
"LLaMA-2 Chat (70B)": "togethercomputer/llama-2-70b-chat",
"LLaMA-2 Chat (7B)": "togethercomputer/llama-2-7b-chat",
"Meta Llama 3 8B Chat": "meta-llama/Llama-3-8b-chat-hf",
"WizardLM-2 (8x22B)": "microsoft/WizardLM-2-8x22B",
"OLMo Instruct (7B)": "allenai/OLMo-7B-Instruct",
"Qwen 1.5 Chat (4B)": "Qwen/Qwen1.5-4B-Chat",
"MythoMax-L2 (13B)": "Gryphe/MythoMax-L2-13b",
"Mistral (7B) Instruct": "mistralai/Mistral-7B-Instruct-v0.1",
"Mistral (7B) Instruct v0.2": "mistralai/Mistral-7B-Instruct-v0.2",
"OpenOrca Mistral (7B) 8K": "Open-Orca/Mistral-7B-OpenOrca",
"01-ai Yi Chat (34B)": "zero-one-ai/Yi-34B-Chat",
"Nous Hermes LLaMA-2 (7B)": "NousResearch/Nous-Hermes-llama-2-7b",
"Qwen 1.5 Chat (32B)": "Qwen/Qwen1.5-32B-Chat",
"DBRX Instruct": "databricks/dbrx-instruct",
"Qwen 2 Instruct (72B)": "Qwen/Qwen2-72B-Instruct",
"Qwen 1.5 Chat (72B)": "Qwen/Qwen1.5-72B-Chat",
"DeepSeek LLM Chat (67B)": "deepseek-ai/deepseek-llm-67b-chat",
"Vicuna v1.5 (7B)": "lmsys/vicuna-7b-v1.5",
"WizardLM-2 (8x22B)": "microsoft/WizardLM-2-8x22B",
"Togethercomputer Llama3 8B Instruct Int8": "togethercomputer/Llama-3-8b-chat-hf-int8",
"Mistral (7B) Instruct v0.3": "mistralai/Mistral-7B-Instruct-v0.3",
"Mixtral-8x22B Instruct v0.1": "mistralai/Mixtral-8x22B-Instruct-v0.1",
"Qwen 1.5 Chat (110B)": "Qwen/Qwen1.5-110B-Chat",
"LLaMA-2 Chat (13B)": "togethercomputer/llama-2-13b-chat",
"Meta Llama 3 8B Chat": "meta-llama/Llama-3-8b-chat-hf",
"Mixtral-8x7B Instruct v0.1": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"OpenChat 3.5": "openchat/openchat-3.5-1210",
"Snorkel Mistral PairRM DPO (7B)": "snorkelai/Snorkel-Mistral-PairRM-DPO",
"OpenHermes-2-Mistral (7B)": "teknium/OpenHermes-2-Mistral-7B",
"OpenHermes-2.5-Mistral (7B)": "teknium/OpenHermes-2p5-Mistral-7B",
"LLaMA-2-7B-32K-Instruct (7B)": "togethercomputer/Llama-2-7B-32K-Instruct",
"StripedHyena Nous (7B)": "togethercomputer/StripedHyena-Nous-7B",
"Alpaca (7B)": "togethercomputer/alpaca-7b",
"Upstage SOLAR Instruct v1 (11B)": "upstage/SOLAR-10.7B-Instruct-v1.0",
"01-ai Yi Chat (34B)": "zero-one-ai/Yi-34B-Chat",
"LLaMA-2 Chat (7B)": "togethercomputer/llama-2-7b-chat",
"LLaMA-2 Chat (70B)": "togethercomputer/llama-2-70b-chat",
"Meta Llama 3 70B Chat": "meta-llama/Llama-3-70b-chat-hf",
"Llama3 8B Chat HF INT4": "togethercomputer/Llama-3-8b-chat-hf-int4",
"Togethercomputer Llama3 8B Instruct Int8": "togethercomputer/Llama-3-8b-chat-hf-int8",
"Reserved - DBRX Instruct": "medaltv/dbrx-instruct",
"Koala (7B)": "togethercomputer/Koala-7B",
"Guanaco (65B) ": "togethercomputer/guanaco-65b",
"Vicuna v1.3 (7B)": "lmsys/vicuna-7b-v1.3",
Expand All @@ -89,6 +89,7 @@
"Meta Llama 3 8B Instruct": "meta-llama/Meta-Llama-3-8B-Instruct",
"Meta Llama 3 70B Instruct": "meta-llama/Meta-Llama-3-70B-Instruct",
"Gemma-2 Instruct (9B)": "google/gemma-2-9b-it",
"Hermes 2 Theta Llama-3 70B": "NousResearch/Hermes-2-Theta-Llama-3-70B",
}

TogetherModels: TypeAlias = Literal[tuple(together_model_string.keys())] # type: ignore[valid-type]
Expand Down
1 change: 1 addition & 0 deletions tests/models/llms/test_together.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ def test_together_model_string(self) -> None:
if model.type == "chat"
}

# print(expected_together_model_string)
assert together_model_string == expected_together_model_string

@pytest.mark.db()
Expand Down

0 comments on commit de83397

Please sign in to comment.