From dc770efb14bd6e18421511912fbb959a3cf9f78d Mon Sep 17 00:00:00 2001 From: hiyouga <467089858@qq.com> Date: Fri, 9 Aug 2024 20:20:35 +0800 Subject: [PATCH] add qwen2 math models --- README.md | 54 ++++++++++++++-------------- README_zh.md | 54 ++++++++++++++-------------- src/llamafactory/extras/constants.py | 24 +++++++++++++ 3 files changed, 78 insertions(+), 54 deletions(-) diff --git a/README.md b/README.md index f3970d00..f21e7403 100644 --- a/README.md +++ b/README.md @@ -153,33 +153,33 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ ## Supported Models -| Model | Model size | Template | -| ------------------------------------------------------------ | -------------------------------- | --------- | -| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 | -| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - | -| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 | -| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere | -| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek | -| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon | -| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma | -| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 | -| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 | -| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - | -| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 | -| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 | -| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | vicuna | -| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B | cpm | -| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | -| [OLMo](https://huggingface.co/allenai) | 1B/7B | - | -| [PaliGemma](https://huggingface.co/google) | 3B | gemma | -| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - | -| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi | -| [Qwen/Qwen1.5/Qwen2 (Code/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen | -| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | -| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse | -| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi | -| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl | -| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan | +| Model | Model size | Template | +| ----------------------------------------------------------------- | -------------------------------- | --------- | +| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 | +| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - | +| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 | +| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere | +| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek | +| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon | +| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma | +| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 | +| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 | +| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - | +| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 | +| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 | +| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | vicuna | +| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B | cpm | +| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | +| [OLMo](https://huggingface.co/allenai) | 1B/7B | - | +| [PaliGemma](https://huggingface.co/google) | 3B | gemma | +| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - | +| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi | +| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen | +| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | +| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse | +| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi | +| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl | +| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan | > [!NOTE] > For the "base" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "instruct/chat" models. diff --git a/README_zh.md b/README_zh.md index 3f93af5d..e70d4e6a 100644 --- a/README_zh.md +++ b/README_zh.md @@ -153,33 +153,33 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272 ## 模型 -| 模型名 | 模型大小 | Template | -| ------------------------------------------------------------ | -------------------------------- | --------- | -| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 | -| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - | -| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 | -| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere | -| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek | -| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon | -| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma | -| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 | -| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 | -| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - | -| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 | -| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 | -| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | vicuna | -| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B | cpm | -| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | -| [OLMo](https://huggingface.co/allenai) | 1B/7B | - | -| [PaliGemma](https://huggingface.co/google) | 3B | gemma | -| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - | -| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi | -| [Qwen/Qwen1.5/Qwen2 (Code/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen | -| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | -| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse | -| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi | -| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl | -| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan | +| 模型名 | 模型大小 | Template | +| ----------------------------------------------------------------- | -------------------------------- | --------- | +| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 | +| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - | +| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 | +| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere | +| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek | +| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon | +| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma | +| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 | +| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 | +| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - | +| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 | +| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 | +| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | vicuna | +| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B | cpm | +| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | +| [OLMo](https://huggingface.co/allenai) | 1B/7B | - | +| [PaliGemma](https://huggingface.co/google) | 3B | gemma | +| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - | +| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi | +| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen | +| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | +| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse | +| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi | +| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl | +| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan | > [!NOTE] > 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。 diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index 4531db4a..80df135c 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -1244,6 +1244,18 @@ register_model_group( DownloadSource.DEFAULT: "Qwen/Qwen2-57B-A14B", DownloadSource.MODELSCOPE: "qwen/Qwen2-57B-A14B", }, + "Qwen2-Math-1.5B": { + DownloadSource.DEFAULT: "Qwen/Qwen2-Math-1.5B", + DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-1.5B", + }, + "Qwen2-Math-7B": { + DownloadSource.DEFAULT: "Qwen/Qwen2-Math-7B", + DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-7B", + }, + "Qwen2-Math-72B": { + DownloadSource.DEFAULT: "Qwen/Qwen2-Math-72B", + DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-72B", + }, "Qwen2-0.5B-Chat": { DownloadSource.DEFAULT: "Qwen/Qwen2-0.5B-Instruct", DownloadSource.MODELSCOPE: "qwen/Qwen2-0.5B-Instruct", @@ -1264,6 +1276,18 @@ register_model_group( DownloadSource.DEFAULT: "Qwen/Qwen2-57B-A14B-Instruct", DownloadSource.MODELSCOPE: "qwen/Qwen2-57B-A14B-Instruct", }, + "Qwen2-Math-1.5B-Chat": { + DownloadSource.DEFAULT: "Qwen/Qwen2-Math-1.5B-Instruct", + DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-1.5B-Instruct", + }, + "Qwen2-Math-7B-Chat": { + DownloadSource.DEFAULT: "Qwen/Qwen2-Math-7B-Instruct", + DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-7B-Instruct", + }, + "Qwen2-Math-72B-Chat": { + DownloadSource.DEFAULT: "Qwen/Qwen2-Math-72B-Instruct", + DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-72B-Instruct", + }, "Qwen2-0.5B-int8-Chat": { DownloadSource.DEFAULT: "Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8", DownloadSource.MODELSCOPE: "qwen/Qwen2-0.5B-Instruct-GPTQ-Int8",