From 1845e039212280b2b46f8f0238827bde85186050 Mon Sep 17 00:00:00 2001 From: hiyouga Date: Wed, 21 Feb 2024 23:27:36 +0800 Subject: [PATCH] support gemma Former-commit-id: c99e19641a9b893da0a3277bd41bd1d3996d1913 --- README.md | 3 ++- README_zh.md | 3 ++- src/llmtuner/data/template.py | 10 ++++++++++ src/llmtuner/extras/constants.py | 19 +++++++++++++++++++ 4 files changed, 33 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index b71303f2..7901685a 100644 --- a/README.md +++ b/README.md @@ -107,6 +107,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ | [ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b) | 6B | query_key_value | chatglm3 | | [DeepSeek (MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B | q_proj,v_proj | deepseek | | [Falcon](https://huggingface.co/tiiuae) | 7B/40B/180B | query_key_value | falcon | +| [Gemma](https://huggingface.co/google) | 2B/7B | q_proj,v_proj | gemma | | [InternLM2](https://huggingface.co/internlm) | 7B/20B | wqkv | intern2 | | [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | q_proj,v_proj | - | | [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 | @@ -601,7 +602,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ This repository is licensed under the [Apache-2.0 License](LICENSE). -Please follow the model licenses to use the corresponding model weights: [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) +Please follow the model licenses to use the corresponding model weights: [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) ## Citation diff --git a/README_zh.md b/README_zh.md index 5c74e67a..ebcddbba 100644 --- a/README_zh.md +++ b/README_zh.md @@ -107,6 +107,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846 | [ChatGLM3](https://huggingface.co/THUDM/chatglm3-6b) | 6B | query_key_value | chatglm3 | | [DeepSeek (MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B | q_proj,v_proj | deepseek | | [Falcon](https://huggingface.co/tiiuae) | 7B/40B/180B | query_key_value | falcon | +| [Gemma](https://huggingface.co/google) | 2B/7B | q_proj,v_proj | gemma | | [InternLM2](https://huggingface.co/internlm) | 7B/20B | wqkv | intern2 | | [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | q_proj,v_proj | - | | [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 | @@ -601,7 +602,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ 本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。 -使用模型权重时，请遵循对应的模型协议：[Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) +使用模型权重时，请遵循对应的模型协议：[Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [InternLM2](https://github.com/InternLM/InternLM#license) / [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [LLaMA-2](https://ai.meta.com/llama/license/) / [Mistral](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) ## 引用 diff --git a/src/llmtuner/data/template.py b/src/llmtuner/data/template.py index 4b2e2e51..523520ea 100644 --- a/src/llmtuner/data/template.py +++ b/src/llmtuner/data/template.py @@ -433,6 +433,16 @@ _register_template( ) +_register_template( + name="gemma", + format_user=StringFormatter(slots=["user\n{{content}}\nmodel\n"]), + format_system=StringFormatter(slots=["{{content}}"]), + format_separator=EmptyFormatter(slots=["\n"]), + stop_words=[""], + replace_eos=True, +) + + _register_template( name="intern", format_user=StringFormatter(slots=["<|User|>:{{content}}", {"token": ""}, "\n<|Bot|>:"]), diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py index 33eb7f42..75775e17 100644 --- a/src/llmtuner/extras/constants.py +++ b/src/llmtuner/extras/constants.py @@ -324,6 +324,25 @@ register_model_group( ) +register_model_group( + models={ + "Gemma-2B": { + DownloadSource.DEFAULT: "google/gemma-2b", + }, + "Gemma-7B": { + DownloadSource.DEFAULT: "google/gemma-7b", + }, + "Gemma-2B-Chat": { + DownloadSource.DEFAULT: "google/gemma-2b-it", + }, + "Gemma-7B-Chat": { + DownloadSource.DEFAULT: "google/gemma-7b-it", + }, + }, + template="gemma", +) + + register_model_group( models={ "InternLM-7B": {