diff --git a/README.md b/README.md index cff7422d..e355691e 100644 --- a/README.md +++ b/README.md @@ -175,7 +175,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ | [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/Llama3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 | +| [Llama 3-3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 | | [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava | | [LLaVA-NeXT](https://huggingface.co/llava-hf) | 7B/8B/13B/34B/72B/110B | llava_next | | [LLaVA-NeXT-Video](https://huggingface.co/llava-hf) | 7B/34B | llava_next_video | diff --git a/README_zh.md b/README_zh.md index 623eb8e5..804704cf 100644 --- a/README_zh.md +++ b/README_zh.md @@ -163,29 +163,29 @@ 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/Llama3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 | -| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava | +| 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 3-3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 | +| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava | | [LLaVA-NeXT](https://huggingface.co/llava-hf) | 7B/8B/13B/34B/72B/110B | llava_next | | [LLaVA-NeXT-Video](https://huggingface.co/llava-hf) | 7B/34B | llava_next_video | -| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 | -| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | -| [OLMo](https://huggingface.co/allenai) | 1B/7B | - | -| [PaliGemma](https://huggingface.co/google) | 3B | paligemma | -| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - | -| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi | +| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 | +| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | +| [OLMo](https://huggingface.co/allenai) | 1B/7B | - | +| [PaliGemma](https://huggingface.co/google) | 3B | paligemma | +| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - | +| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi | | [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen | | [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B/72B | qwen2_vl | | [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | diff --git a/src/llamafactory/model/model_utils/attention.py b/src/llamafactory/model/model_utils/attention.py index 96e2c8a9..7667b069 100644 --- a/src/llamafactory/model/model_utils/attention.py +++ b/src/llamafactory/model/model_utils/attention.py @@ -37,10 +37,11 @@ def configure_attn_implementation( if is_flash_attn_2_available(): require_version("transformers>=4.42.4", "To fix: pip install transformers>=4.42.4") require_version("flash_attn>=2.6.3", "To fix: pip install flash_attn>=2.6.3") - logger.warning("Gemma-2 should use flash attention 2, change `flash_attn` to fa2.") - model_args.flash_attn = "fa2" + if model_args.flash_attn != "fa2": + logger.warning("Gemma-2 should use flash attention 2, change `flash_attn` to fa2.") + model_args.flash_attn = "fa2" else: - logger.warning("Gemma-2 should use eager attention, change `flash_attn` to disabled.") + logger.warning("FlashAttention-2 is not installed, use eager attention.") model_args.flash_attn = "disabled" elif model_args.flash_attn == "sdpa": logger.warning("Gemma-2 should use soft-capping attention, while the SDPA attention does not support it.")