From 3d6a80660e6b8fe0f54bf132a08e6df57584847a Mon Sep 17 00:00:00 2001 From: hiyouga Date: Mon, 13 May 2024 16:51:20 +0800 Subject: [PATCH] support Yi 1.5 Former-commit-id: d12b8f866aa51e5e22d2b3d29704a13308de3e5b --- README.md | 4 +-- README_zh.md | 4 +-- src/llmtuner/extras/constants.py | 39 +++++++++++++++++++++++----- src/llmtuner/model/utils/longlora.py | 2 +- 4 files changed, 38 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 57a34dab..d260ad36 100644 --- a/README.md +++ b/README.md @@ -161,7 +161,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ | [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen) | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | q_proj,v_proj | qwen | | [StarCoder2](https://huggingface.co/bigcode) | 3B/7B/15B | q_proj,v_proj | - | | [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | q_proj,v_proj | xverse | -| [Yi](https://huggingface.co/01-ai) | 6B/9B/34B | q_proj,v_proj | yi | +| [Yi (1/1.5)](https://huggingface.co/01-ai) | 6B/9B/34B | q_proj,v_proj | yi | | [Yuan](https://huggingface.co/IEITYuan) | 2B/51B/102B | q_proj,v_proj | yuan | > [!NOTE] @@ -487,7 +487,7 @@ If you have a project that should be incorporated, please contact via email or c 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) / [Command-R](https://cohere.com/c4ai-cc-by-nc-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/LLaVA-1.5](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [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) / [Command-R](https://cohere.com/c4ai-cc-by-nc-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 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [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) / [Yi-1.5](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 047b1645..8912d5e1 100644 --- a/README_zh.md +++ b/README_zh.md @@ -161,7 +161,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd | [Qwen1.5 (Code/MoE)](https://huggingface.co/Qwen) | 0.5B/1.8B/4B/7B/14B/32B/72B/110B | q_proj,v_proj | qwen | | [StarCoder2](https://huggingface.co/bigcode) | 3B/7B/15B | q_proj,v_proj | - | | [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | q_proj,v_proj | xverse | -| [Yi](https://huggingface.co/01-ai) | 6B/9B/34B | q_proj,v_proj | yi | +| [Yi (1/1.5)](https://huggingface.co/01-ai) | 6B/9B/34B | q_proj,v_proj | yi | | [Yuan](https://huggingface.co/IEITYuan) | 2B/51B/102B | q_proj,v_proj | yuan | > [!NOTE] @@ -487,7 +487,7 @@ export USE_MODELSCOPE_HUB=1 # Windows 使用 `set USE_MODELSCOPE_HUB=1` 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) / [Command-R](https://cohere.com/c4ai-cc-by-nc-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/LLaVA-1.5](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [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) / [Command-R](https://cohere.com/c4ai-cc-by-nc-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 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [LLaMA-3](https://llama.meta.com/llama3/license/) / [Mistral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [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) / [Yi-1.5](LICENSE) / [Yuan](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) ## 引用 diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py index 50c78b3f..ff52f29a 100644 --- a/src/llmtuner/extras/constants.py +++ b/src/llmtuner/extras/constants.py @@ -320,14 +320,14 @@ register_model_group( DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base", DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base", }, + "DeepSeek-MoE-236B-Base": { + DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2", + DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2", + }, "DeepSeek-MoE-16B-Chat": { DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat", DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat", }, - "DeepSeek-MoE-236B": { - DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2", - DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2", - }, "DeepSeek-MoE-236B-Chat": { DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2-Chat", DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2-Chat", @@ -424,13 +424,13 @@ register_model_group( register_model_group( models={ "CodeGemma-2B": { - DownloadSource.DEFAULT: "google/codegemma-2b", + DownloadSource.DEFAULT: "google/codegemma-1.1-2b", }, "CodeGemma-7B": { DownloadSource.DEFAULT: "google/codegemma-7b", }, "CodeGemma-7B-Chat": { - DownloadSource.DEFAULT: "google/codegemma-7b-it", + DownloadSource.DEFAULT: "google/codegemma-1.1-7b-it", DownloadSource.MODELSCOPE: "AI-ModelScope/codegemma-7b-it", }, }, @@ -581,6 +581,9 @@ register_model_group( DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat", DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat", }, + "LLaMA3-70B-Chinese-Chat": { + DownloadSource.DEFAULT: "shenzhi-wang/Llama3-70B-Chinese-Chat", + }, }, template="llama3", ) @@ -1174,6 +1177,30 @@ register_model_group( DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat-4bits", DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat-4bits", }, + "Yi-1.5-6B": { + DownloadSource.DEFAULT: "01-ai/Yi-1.5-6B", + DownloadSource.MODELSCOPE: "01ai/Yi-1.5-6B", + }, + "Yi-1.5-9B": { + DownloadSource.DEFAULT: "01-ai/Yi-1.5-9B", + DownloadSource.MODELSCOPE: "01ai/Yi-1.5-9B", + }, + "Yi-1.5-34B": { + DownloadSource.DEFAULT: "01-ai/Yi-1.5-34B", + DownloadSource.MODELSCOPE: "01ai/Yi-1.5-34B", + }, + "Yi-1.5-6B-Chat": { + DownloadSource.DEFAULT: "01-ai/Yi-1.5-6B-Chat", + DownloadSource.MODELSCOPE: "01ai/Yi-1.5-6B-Chat", + }, + "Yi-1.5-9B-Chat": { + DownloadSource.DEFAULT: "01-ai/Yi-1.5-9B-Chat", + DownloadSource.MODELSCOPE: "01ai/Yi-1.5-9B-Chat", + }, + "Yi-1.5-34B-Chat": { + DownloadSource.DEFAULT: "01-ai/Yi-1.5-34B-Chat", + DownloadSource.MODELSCOPE: "01ai/Yi-1.5-34B-Chat", + }, }, template="yi", ) diff --git a/src/llmtuner/model/utils/longlora.py b/src/llmtuner/model/utils/longlora.py index c91febdd..a11351f1 100644 --- a/src/llmtuner/model/utils/longlora.py +++ b/src/llmtuner/model/utils/longlora.py @@ -302,7 +302,7 @@ def llama_sdpa_attention_forward( def _apply_llama_patch() -> None: - require_version("transformers==4.40.1", "To fix: pip install transformers==4.40.1") + require_version("transformers==4.40.2", "To fix: pip install transformers==4.40.2") LlamaAttention.forward = llama_attention_forward LlamaFlashAttention2.forward = llama_flash_attention_2_forward LlamaSdpaAttention.forward = llama_sdpa_attention_forward