From 1f9ad5f2aeab2b2cf0d29e03416f3b634e2c7bbd Mon Sep 17 00:00:00 2001 From: Kumaran Rajendhiran Date: Mon, 29 Jul 2024 10:15:08 +0000 Subject: [PATCH] Update togetherai model string --- fastagency/models/llms/together.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fastagency/models/llms/together.py b/fastagency/models/llms/together.py index 054c6ae90..df1197b05 100644 --- a/fastagency/models/llms/together.py +++ b/fastagency/models/llms/together.py @@ -21,7 +21,6 @@ "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", - "Meta Llama 3.1 8B Instruct Turbo": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "OpenChat 3.5": "openchat/openchat-3.5-1210", "Chronos Hermes (13B)": "Austism/chronos-hermes-13b", "Snorkel Mistral PairRM DPO (7B)": "snorkelai/Snorkel-Mistral-PairRM-DPO", @@ -38,7 +37,6 @@ "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", - "Meta Llama 3.1 70B Instruct Turbo": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "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", @@ -54,9 +52,12 @@ "Meta Llama 3 70B Reference": "meta-llama/Llama-3-70b-chat-hf", "Mistral (7B) Instruct": "mistralai/Mistral-7B-Instruct-v0.1", "Mistral (7B) Instruct v0.2": "mistralai/Mistral-7B-Instruct-v0.2", + "Meta Llama 3.1 8B Instruct Turbo": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "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", + "Meta Llama 3.1 405B Instruct Turbo": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", + "Meta Llama 3.1 70B Instruct Turbo": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "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", @@ -82,7 +83,6 @@ "Meta Llama 3 8B Instruct Lite": "meta-llama/Meta-Llama-3-8B-Instruct-Lite", "LLaMA-2 Chat (7B)": "togethercomputer/llama-2-7b-chat", "LLaMA-2 Chat (70B)": "togethercomputer/llama-2-70b-chat", - "Meta Llama 3.1 405B Instruct Turbo": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "Koala (7B)": "togethercomputer/Koala-7B", "Qwen 2 Instruct (1.5B)": "Qwen/Qwen2-1.5B-Instruct", "Qwen 2 Instruct (7B)": "Qwen/Qwen2-7B-Instruct", @@ -109,7 +109,6 @@ "carson ml318br": "carson/ml318br", "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", - "Meta Llama 3.1 70B": "meta-llama/Meta-Llama-3.1-70B-Reference", } TogetherModels: TypeAlias = Literal[tuple(together_model_string.keys())] # type: ignore[valid-type]