From 14ed926a2d37c0bd32c048d7943605b91f85aad7 Mon Sep 17 00:00:00 2001 From: hiyouga Date: Tue, 12 Mar 2024 18:30:38 +0800 Subject: [PATCH] support olmo Former-commit-id: b3247d6a1604f4cbeb0d7c163d0082ce91afb870 --- README.md | 3 ++- README_zh.md | 3 ++- src/llmtuner/data/template.py | 9 +++++++++ src/llmtuner/extras/constants.py | 18 ++++++++++++++++++ 4 files changed, 31 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index a0c16008..9f33b539 100644 --- a/README.md +++ b/README.md @@ -134,6 +134,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ | [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 | | [Mistral](https://huggingface.co/mistralai) | 7B | q_proj,v_proj | mistral | | [Mixtral](https://huggingface.co/mistralai) | 8x7B | q_proj,v_proj | mistral | +| [OLMo](https://huggingface.co/allenai) | 1B/7B | att_proj | olmo | | [Phi-1.5/2](https://huggingface.co/microsoft) | 1.3B/2.7B | q_proj,v_proj | - | | [Qwen](https://huggingface.co/Qwen) | 1.8B/7B/14B/72B | c_attn | qwen | | [Qwen1.5](https://huggingface.co/Qwen) | 0.5B/1.8B/4B/7B/14B/72B | q_proj,v_proj | qwen | @@ -708,7 +709,7 @@ docker compose -f ./docker-compose.yml up -d 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) / [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) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [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) / [OLMo](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) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [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 d034edc8..2dfb3771 100644 --- a/README_zh.md +++ b/README_zh.md @@ -134,6 +134,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd | [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 | | [Mistral](https://huggingface.co/mistralai) | 7B | q_proj,v_proj | mistral | | [Mixtral](https://huggingface.co/mistralai) | 8x7B | q_proj,v_proj | mistral | +| [OLMo](https://huggingface.co/allenai) | 1B/7B | att_proj | olmo | | [Phi-1.5/2](https://huggingface.co/microsoft) | 1.3B/2.7B | q_proj,v_proj | - | | [Qwen](https://huggingface.co/Qwen) | 1.8B/7B/14B/72B | c_attn | qwen | | [Qwen1.5](https://huggingface.co/Qwen) | 0.5B/1.8B/4B/7B/14B/72B | q_proj,v_proj | qwen | @@ -681,7 +682,7 @@ 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) / [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) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [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) / [OLMo](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) / [StarCoder2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [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 2a2a9970..af80272b 100644 --- a/src/llmtuner/data/template.py +++ b/src/llmtuner/data/template.py @@ -631,6 +631,15 @@ _register_template( ) +_register_template( + name="olmo", + format_user=StringFormatter(slots=["<|user|>\n{{content}}<|assistant|>"]), + format_assistant=StringFormatter(slots=["{{content}}", {"eos_token"}]), + format_system=StringFormatter(slots=[{"eos_token"}, "{{content}}"]), + force_system=True, +) + + _register_template( name="openchat", format_user=StringFormatter(slots=["GPT4 Correct User: {{content}}", {"eos_token"}, "GPT4 Correct Assistant:"]), diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py index 93036ac4..03d93cc2 100644 --- a/src/llmtuner/extras/constants.py +++ b/src/llmtuner/extras/constants.py @@ -492,6 +492,24 @@ register_model_group( ) +register_model_group( + models={ + "OLMo-1B": { + DownloadSource.DEFAULT: "allenai/OLMo-1B", + }, + "OLMo-7B": { + DownloadSource.DEFAULT: "allenai/OLMo-7B", + DownloadSource.MODELSCOPE: "AI-ModelScope/OLMo-7B", + }, + "OLMo-7B-Chat": { + DownloadSource.DEFAULT: "allenai/OLMo-7B-Instruct", + } + }, + module="att_proj", + template="olmo", +) + + register_model_group( models={ "OpenChat3.5-7B-Chat": {