From 4aea71dd92d8783015c29ff00fe65b409a322c96 Mon Sep 17 00:00:00 2001 From: Aaron Pham Date: Thu, 26 Sep 2024 04:31:18 -0400 Subject: [PATCH] chore: update README.md models (#23) Signed-off-by: Aaron Pham --- README.md | 41 ----------------------------------------- gen_readme.py | 3 +-- 2 files changed, 1 insertion(+), 43 deletions(-) diff --git a/README.md b/README.md index 08410200..d00b42c7 100644 --- a/README.md +++ b/README.md @@ -24,9 +24,6 @@ openllm repo add nightly https://github.com/bentoml/openllm-models@nightly - [Mistral-Large](#mistral-large) - [Codestral](#codestral) - [Llama-3](#llama3) -- [Qwen-2](#qwen2) -- [](#llama2) -- [Gemma](#gemma) --- @@ -140,41 +137,3 @@ openllm repo add nightly https://github.com/bentoml/openllm-models@nightly --- - -### Qwen-2 - -| Model | Version | Huggingface Link | -| --- | --- | --- | -| qwen2 | 0.5b-instruct-fp16-114e | [HF Link](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) | -| qwen2 | 1.5b-instruct-fp16-743d | [HF Link](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) | -| qwen2 | 57b-a14b-instruct-fp16-13ca | [HF Link](https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct) | -| qwen2 | 72b-instruct-awq-4bit-5384 | [HF Link](https://huggingface.co/Qwen/Qwen2-72B-Instruct-AWQ) | -| qwen2 | 72b-instruct-fp16-4755 | [HF Link](https://huggingface.co/Qwen/Qwen2-72B-Instruct) | -| qwen2 | 7b-instruct-awq-4bit-89de | [HF Link](https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ) | -| qwen2 | 7b-instruct-fp16-c17f | [HF Link](https://huggingface.co/Qwen/Qwen2-7B-Instruct) | - ---- - - -### - -| Model | Version | Huggingface Link | -| --- | --- | --- | -| llama2 | 13b-chat-fp16-15d8 | [HF Link](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) | -| llama2 | 70b-chat-fp16-8365 | [HF Link](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) | -| llama2 | 7b-chat-awq-4bit-8f2f | [HF Link](https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ) | -| llama2 | 7b-chat-fp16-5e52 | [HF Link](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) | - ---- - - -### Gemma - -| Model | Version | Huggingface Link | -| --- | --- | --- | -| gemma | 2b-instruct-fp16-e12f | [HF Link](https://huggingface.co/google/gemma-2b-it) | -| gemma | 7b-instruct-awq-4bit-1134 | [HF Link](https://huggingface.co/casperhansen/gemma-7b-it-awq) | -| gemma | 7b-instruct-fp16-e12a | [HF Link](https://huggingface.co/google/gemma-7b-it) | - ---- - diff --git a/gen_readme.py b/gen_readme.py index 8cd67e25..5af64e73 100644 --- a/gen_readme.py +++ b/gen_readme.py @@ -13,9 +13,7 @@ "llama3": "Llama-3", "phi3": "Phi-3", "mistral": "Mistral", - "qwen2": "Qwen-2", "qwen2.5": "Qwen-2.5", - "gemma": "Gemma", "gemma2": "Gemma-2", "mixtral": "Mixtral", "mistral-large": "Mistral-Large", @@ -40,6 +38,7 @@ for yaml_file in yaml_files: with open(yaml_file, "r") as f: data = yaml.safe_load(f) + if data['name'] not in model_display_names: continue # Extract the HF model ID from routes.input.model.default for route in data.get("schema", {}).get("routes", []): for prop, details in route.get("input", {}).get("properties", {}).items():