Skip to content

Commit

Permalink
Fix together AI tests
Browse files Browse the repository at this point in the history
  • Loading branch information
@harishmohanraj
harishmohanraj committed Nov 27, 2024
1 parent 982caf0 commit fb8bdf2
Show file tree
Hide file tree
Showing 2 changed files with 43 additions and 39 deletions.
80 changes: 42 additions & 38 deletions fastagency_studio/models/llms/together.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,55 +15,56 @@
# retrieve the models from the API on Nov 11, 2024
together_model_string = {
"Code Llama Instruct (34B)": "togethercomputer/CodeLlama-34b-Instruct",
"Upstage SOLAR Instruct v1 (11B)": "upstage/SOLAR-10.7B-Instruct-v1.0",
"Meta Llama 3.1 70B Instruct Turbo": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
"WizardLM-2 (8x22B)": "microsoft/WizardLM-2-8x22B",
"Meta Llama 3.2 11B Vision Instruct Turbo": "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
"Meta Llama 3.2 90B Vision Instruct Turbo": "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
"Meta Llama Vision Free": "meta-llama/Llama-Vision-Free",
"Llama3 8B Chat HF INT4": "togethercomputer/Llama-3-8b-chat-hf-int4",
"Gemma Instruct (2B)": "google/gemma-2b-it",
"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",
"Meta Llama 3.1 405B Instruct Turbo": "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro",
"DeepSeek LLM Chat (67B)": "deepseek-ai/deepseek-llm-67b-chat",
"Togethercomputer Llama3 8B Instruct Int8": "togethercomputer/Llama-3-8b-chat-hf-int8",
"Mistral (7B) Instruct v0.3": "mistralai/Mistral-7B-Instruct-v0.3",
"LLaMA-2 Chat (13B)": "togethercomputer/llama-2-13b-chat",
"Meta Llama 3 70B Instruct Turbo": "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
"Meta Llama 3 70B Instruct Lite": "meta-llama/Meta-Llama-3-70B-Instruct-Lite",
"Meta Llama 3.2 3B Instruct Turbo": "meta-llama/Llama-3.2-3B-Instruct-Turbo",
"Gemma-2 Instruct (27B)": "google/gemma-2-27b-it",
"Mixtral-8x22B Instruct v0.1": "mistralai/Mixtral-8x22B-Instruct-v0.1",
"Meta Llama 3 70B Instruct Reference": "meta-llama/Llama-3-70b-chat-hf",
"Typhoon 1.5X 70B-awq": "scb10x/scb10x-llama3-typhoon-v1-5x-4f316",
"Qwen2.5 7B Instruct Turbo": "Qwen/Qwen2.5-7B-Instruct-Turbo",
"Qwen 2 Instruct (72B)": "Qwen/Qwen2-72B-Instruct",
"Meta Llama 3 8B Instruct Reference": "meta-llama/Llama-3-8b-chat-hf",
"Qwen2.5 72B Instruct Turbo": "Qwen/Qwen2.5-72B-Instruct-Turbo",
"Meta Llama 3.1 70B Instruct Turbo": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
"Llama 3.1 Nemotron 70B Instruct HF": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
"Qwen 2.5 Coder 32B Instruct": "Qwen/Qwen2.5-Coder-32B-Instruct",
"MythoMax-L2 (13B)": "Gryphe/MythoMax-L2-13b",
"Mixtral-8x7B Instruct v0.1": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"Meta Llama 3.2 90B Vision Instruct Turbo": "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
"Meta Llama 3.2 11B Vision Instruct Turbo": "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
"Nous Hermes 2 - Mixtral 8x7B-DPO ": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"DeepSeek LLM Chat (67B)": "deepseek-ai/deepseek-llm-67b-chat",
"LLaVa-Next (Mistral-7B)": "llava-hf/llava-v1.6-mistral-7b-hf",
"Upstage SOLAR Instruct v1 (11B)": "upstage/SOLAR-10.7B-Instruct-v1.0",
"LLaMA-2 Chat (13B)": "togethercomputer/llama-2-13b-chat",
"DBRX Instruct": "databricks/dbrx-instruct",
"Nous Hermes 2 - Mixtral 8x7B-DPO ": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"Meta Llama 3 70B Instruct Reference": "meta-llama/Llama-3-70b-chat-hf",
"Qwen2.5 7B Instruct Turbo": "Qwen/Qwen2.5-7B-Instruct-Turbo",
"Meta Llama 3.2 3B Instruct Turbo": "meta-llama/Llama-3.2-3B-Instruct-Turbo",
"Meta Llama 3.1 405B Instruct Turbo": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
"Meta Llama 3 8B Instruct Lite": "meta-llama/Meta-Llama-3-8B-Instruct-Lite",
"Typhoon 1.5 8B Instruct": "scb10x/scb10x-llama3-typhoon-v1-5-8b-instruct",
"Gemma Instruct (2B)": "google/gemma-2b-it",
"Mistral (7B) Instruct v0.2": "mistralai/Mistral-7B-Instruct-v0.2",
"Mistral (7B) Instruct": "mistralai/Mistral-7B-Instruct-v0.1",
"Mistral (7B) Instruct v0.3": "mistralai/Mistral-7B-Instruct-v0.3",
"Meta Llama 3 70B Instruct Turbo": "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
"Meta Llama 3 70B Instruct Lite": "meta-llama/Meta-Llama-3-70B-Instruct-Lite",
"Meta Llama 3.1 8B Instruct Turbo": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
"Qwen 2 Instruct (72B)": "Qwen/Qwen2-72B-Instruct",
"WizardLM-2 (8x22B)": "microsoft/WizardLM-2-8x22B",
"Mixtral-8x22B Instruct v0.1": "mistralai/Mixtral-8x22B-Instruct-v0.1",
"Gemma-2 Instruct (9B)": "google/gemma-2-9b-it",
"Gryphe MythoMax L2 Lite (13B)": "Gryphe/MythoMax-L2-13b-Lite",
"LLaMA-2 Chat (7B)": "togethercomputer/llama-2-7b-chat",
"Meta Llama Vision Free": "meta-llama/Llama-Vision-Free",
"Gemma-2 Instruct (9B)": "google/gemma-2-9b-it",
"Togethercomputer Llama3 8B Instruct Int8": "togethercomputer/Llama-3-8b-chat-hf-int8",
"WizardLM v1.2 (13B)": "WizardLM/WizardLM-13B-V1.2",
"Koala (7B)": "togethercomputer/Koala-7B",
"Qwen 2 Instruct (1.5B)": "Qwen/Qwen2-1.5B-Instruct",
"OpenHermes-2-Mistral (7B)": "teknium/OpenHermes-2-Mistral-7B",
"Qwen 2 Instruct (7B)": "Qwen/Qwen2-7B-Instruct",
"Guanaco (65B) ": "togethercomputer/guanaco-65b",
"ReMM SLERP L2 (13B)": "Undi95/ReMM-SLERP-L2-13B",
"Nous Capybara v1.9 (7B)": "NousResearch/Nous-Capybara-7B-V1p9",
"Vicuna v1.3 (7B)": "lmsys/vicuna-7b-v1.3",
"Toppy M (7B)": "Undi95/Toppy-M-7B",
"Nous Hermes LLaMA-2 (70B)": "NousResearch/Nous-Hermes-Llama2-70b",
"Vicuna v1.5 16K (13B)": "lmsys/vicuna-13b-v1.5-16k",
"OpenChat 3.5": "openchat/openchat-3.5-1210",
"Zephyr-7B-ß": "HuggingFaceH4/zephyr-7b-beta",
"Chronos Hermes (13B)": "Austism/chronos-hermes-13b",
"Snorkel Mistral PairRM DPO (7B)": "snorkelai/Snorkel-Mistral-PairRM-DPO",
"Qwen 1.5 Chat (14B)": "Qwen/Qwen1.5-14B-Chat",
"Qwen 1.5 Chat (1.8B)": "Qwen/Qwen1.5-1.8B-Chat",
Expand All @@ -75,37 +76,40 @@
"Vicuna v1.5 (13B)": "lmsys/vicuna-13b-v1.5",
"Guanaco (13B) ": "togethercomputer/guanaco-13b",
"Code Llama Instruct (13B)": "togethercomputer/CodeLlama-13b-Instruct",
"Vicuna v1.3 (13B)": "lmsys/vicuna-13b-v1.3",
"Nous Hermes 2 - Mistral DPO (7B)": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
"Alpaca (7B)": "togethercomputer/alpaca-7b",
"Platypus2 Instruct (70B)": "garage-bAInd/Platypus2-70B-instruct",
"Gemma Instruct (7B)": "google/gemma-7b-it",
"OLMo Instruct (7B)": "allenai/OLMo-7B-Instruct",
"Guanaco (33B) ": "togethercomputer/guanaco-33b",
"Koala (13B)": "togethercomputer/Koala-13B",
"Upstage SOLAR Instruct v1 (11B)-Int4": "togethercomputer/SOLAR-10.7B-Instruct-v1.0-int4",
"Guanaco (7B) ": "togethercomputer/guanaco-7b",
"OpenOrca Mistral (7B) 8K": "Open-Orca/Mistral-7B-OpenOrca",
"Nous Hermes LLaMA-2 (7B)": "NousResearch/Nous-Hermes-llama-2-7b",
"Qwen 1.5 Chat (32B)": "Qwen/Qwen1.5-32B-Chat",
"Nous Capybara v1.9 (7B)": "NousResearch/Nous-Capybara-7B-V1p9",
"Meta Llama 3 8B Instruct": "meta-llama/Meta-Llama-3-8B-Instruct",
"Vicuna v1.5 (7B)": "lmsys/vicuna-7b-v1.5",
"OpenHermes-2.5-Mistral (7B)": "teknium/OpenHermes-2p5-Mistral-7B",
"Qwen 1.5 Chat (4B)": "Qwen/Qwen1.5-4B-Chat",
"Qwen 1.5 Chat (0.5B)": "Qwen/Qwen1.5-0.5B-Chat",
"LLaMA-2 Chat (70B)": "togethercomputer/llama-2-70b-chat",
"01-ai Yi Chat (34B)": "zero-one-ai/Yi-34B-Chat",
"Meta Llama 3 70B Instruct": "meta-llama/Meta-Llama-3-70B-Instruct",
"Code Llama Instruct (70B)": "codellama/CodeLlama-70b-Instruct-hf",
"Koala (7B)": "togethercomputer/Koala-7B",
"Hermes 2 Theta Llama-3 70B": "NousResearch/Hermes-2-Theta-Llama-3-70B",
"Test 11": "test/test11",
"Qwen 1.5 Chat (7B)": "Qwen/Qwen1.5-7B-Chat",
"Dolphin 2.5 Mixtral 8x7b": "cognitivecomputations/dolphin-2.5-mixtral-8x7b",
"LLaMA-2 Chat (70B)": "meta-llama/Llama-2-70b-chat-hf",
"Qwen 1.5 Chat (0.5B)": "Qwen/Qwen1.5-0.5B-Chat",
"OpenHermes-2.5-Mistral (7B)": "teknium/OpenHermes-2p5-Mistral-7B",
"Qwen 1.5 Chat (4B)": "Qwen/Qwen1.5-4B-Chat",
"carson ml318br": "carson/ml318br",
"Meta Llama 3.1 8B Instruct": "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference",
"Llama-3 70B Instruct Gradient 1048K": "gradientai/Llama-3-70B-Instruct-Gradient-1048k",
"Meta Llama 3.1 70B Instruct": "meta-llama/Meta-Llama-3.1-70B-Instruct-Reference",
"Qwen 2 Instruct (1.5B)": "Qwen/Qwen2-1.5B-Instruct",
"Zephyr-7B-ß": "HuggingFaceH4/zephyr-7b-beta",
"Chronos Hermes (13B)": "Austism/chronos-hermes-13b",
"Vicuna v1.3 (13B)": "lmsys/vicuna-13b-v1.3",
"Platypus2 Instruct (70B)": "garage-bAInd/Platypus2-70B-instruct",
"OLMo Instruct (7B)": "allenai/OLMo-7B-Instruct",
"Koala (13B)": "togethercomputer/Koala-13B",
"Vicuna v1.5 (7B)": "lmsys/vicuna-7b-v1.5",
}

TogetherModels: TypeAlias = Literal[tuple(together_model_string.keys())] # type: ignore[valid-type]
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ dependencies = [
"fastapi==0.115.5",
"prisma>=0.13.1,<0.16",
"asyncer==0.0.8",
"markdownify==0.14.1", # Needed by autogen.WebSurferAgent but not included
"markdownify==0.13.1", # Needed by autogen.WebSurferAgent but not included
"httpx==0.27.2",
"python-weather==2.0.7", # should be removed when we move API to another project
]
Expand Down

0 comments on commit fb8bdf2

Please sign in to comment.