From 15d17a1e862faa425a6f1befff3bd37d871b265c Mon Sep 17 00:00:00 2001 From: hoshi-hiyouga Date: Fri, 19 Apr 2024 01:13:50 +0800 Subject: [PATCH] support llama3 Former-commit-id: 2aaaede2470a0bb8ce3aabb19c1e11a5f20e36e8 --- README.md | 9 ++++++--- README_zh.md | 9 ++++++--- src/llmtuner/data/template.py | 14 ++++++++++++++ src/llmtuner/extras/constants.py | 19 +++++++++++++++++++ 4 files changed, 45 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 476f6fe6..365f8b34 100644 --- a/README.md +++ b/README.md @@ -68,14 +68,16 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ ## Changelog +[24/04/19] We supported **Meta Llama 3** model series. + [24/04/16] We supported **[BAdam](https://arxiv.org/abs/2404.02827)**. See `examples/extras/badam` for usage. [24/04/16] We supported **[unsloth](https://github.com/unslothai/unsloth)**'s long-sequence training (Llama-2-7B-56k within 24GB). It achieves **117%** speed and **50%** memory compared with FlashAttention-2, more benchmarks can be found in [this page](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison). -[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See `examples/lora_single_gpu` for usage. -
Full Changelog +[24/03/31] We supported **[ORPO](https://arxiv.org/abs/2403.07691)**. See `examples/lora_single_gpu` for usage. + [24/03/21] Our paper "[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)" is available at arXiv! [24/03/20] We supported **FSDP+QLoRA** that fine-tunes a 70B model on 2x24GB GPUs. See `examples/extras/fsdp_qlora` for usage. @@ -143,6 +145,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ | [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 | +| [LLaMA-3](https://huggingface.co/meta-llama) | 8B/70B | q_proj,v_proj | llama3 | | [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | 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 | - | @@ -438,7 +441,7 @@ 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](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) +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](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) / [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 0013c074..ac9e1426 100644 --- a/README_zh.md +++ b/README_zh.md @@ -68,14 +68,16 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd ## 更新日志 +[24/04/19] 我们支持了 **Meta Llama 3** 系列模型。 + [24/04/16] 我们支持了 **[BAdam](https://arxiv.org/abs/2404.02827)**。详细用法请参照 `examples/extras/badam`。 [24/04/16] 我们支持了 **[unsloth](https://github.com/unslothai/unsloth)** 的长序列训练（24GB 可训练 Llama-2-7B-56k）。该方法相比 FlashAttention-2 提供了 **117%** 的训练速度和 **50%** 的显存节约。更多数据请见[此页面](https://github.com/hiyouga/LLaMA-Factory/wiki/Performance-comparison)。 -[24/03/31] 我们支持了 **[ORPO](https://arxiv.org/abs/2403.07691)**。详细用法请参照 `examples/lora_single_gpu`。 -
展开日志 +[24/03/31] 我们支持了 **[ORPO](https://arxiv.org/abs/2403.07691)**。详细用法请参照 `examples/lora_single_gpu`。 + [24/03/21] 我们的论文 "[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://arxiv.org/abs/2403.13372)" 可在 arXiv 上查看！ [24/03/20] 我们支持了能在 2x24GB GPU 上微调 70B 模型的 **FSDP+QLoRA**。详细用法请参照 `examples/extras/fsdp_qlora`。 @@ -143,6 +145,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd | [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 | +| [LLaMA-3](https://huggingface.co/meta-llama) | 8B/70B | q_proj,v_proj | llama3 | | [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | 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 | - | @@ -438,7 +441,7 @@ 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](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) +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](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) / [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 286280e6..00bdbf10 100644 --- a/src/llmtuner/data/template.py +++ b/src/llmtuner/data/template.py @@ -649,6 +649,20 @@ _register_template( ) +_register_template( + name="llama3", + format_user=StringFormatter( + slots=[ + "<|start_header_id|>user<|end_header_id|>\n\n{{content}}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" + ] + ), + format_system=StringFormatter(slots=[{"bos_token"}, "{{content}}"]), + format_separator=EmptyFormatter(slots=["<|eot_id|>"]), + efficient_eos=True, + force_system=True, +) + + _register_template( name="llama2_zh", format_user=StringFormatter(slots=[{"bos_token"}, "[INST] {{content}} [/INST]"]), diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py index cacb6c5f..07ccbc0d 100644 --- a/src/llmtuner/extras/constants.py +++ b/src/llmtuner/extras/constants.py @@ -513,6 +513,25 @@ register_model_group( ) +register_model_group( + models={ + "LLaMA3-8B": { + DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-8B", + }, + "LLaMA3-70B": { + DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-70B", + }, + "LLaMA3-8B-Chat": { + DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-8B-Instruct", + }, + "LLaMA3-70B-Chat": { + DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-70B-Instruct", + }, + }, + template="llama3", +) + + register_model_group( models={ "Mistral-7B-v0.1": {