Skip to content

Commit a1fdc52

Browse files
Jintao-HuangJintao-Huang
committed
Merge branch 'main' into release/2.0
2 parents 5d091cc + 410d952 commit a1fdc52

File tree

12 files changed

+211
-25
lines changed

12 files changed

+211
-25
lines changed

‎README.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -39,6 +39,7 @@ To facilitate use by users unfamiliar with deep learning, we provide a Gradio we
3939
Additionally, we are expanding capabilities for other modalities. Currently, we support full-parameter training and LoRA training for AnimateDiff.
4040

4141
## 🎉 News
42+
- 2024.04.19: Support for inference, fine-tuning, and deployment of **Llama3** series models. This includes: Llama-3-8B, Llama-3-8B-Instruct, Llama-3-70B, and Llama-3-70B-Instruct. use [this script](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/llama3_8b_instruct/lora/sft.sh) to train.
4243
- 2024.04.18: Supported models: wizardlm2-7b-awq, wizardlm2-8x22b, yi-6b-chat-awq, yi-6b-chat-int8, yi-34b-chat-awq, yi-34b-chat-int8. Supported `--deepspeed zero3-offload` and provided default zero3-offload configuration file for zero3+cpu offload usage.
4344
- 2024.04.18: Supported compatibility with HuggingFace ecosystem using the environment variable `USE_HF`, switching to use models and datasets from HF. Please refer to the [HuggingFace ecosystem compatibility documentation](https://github.com/modelscope/swift/tree/main/docs/source_en/LLM/Compat-HF.md).
4445
- 2024.04.17: Support the evaluation for OpenAI standard interfaces. Check the [parameter documentation](docs/source_en/LLM/Command-line-parameters.md#eval-parameters) for details.
@@ -408,6 +409,7 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
408409
| Yuan2 | [Langchao Yuan series models](https://github.com/IEIT-Yuan) | Chinese<br>English | 2B-102B | instruct model |
409410
| XVerse | [XVerse series models](https://github.com/xverse-ai) | Chinese<br>English | 7B-65B | base model<br>chat model<br>long text model<br>MoE model |
410411
| LLaMA2 | [LLaMA2 series models](https://github.com/facebookresearch/llama) | English | 7B-70B<br>including quantized versions | base model<br>chat model |
412+
| LLaMA3 | [LLaMA3 series models](https://github.com/meta-llama/llama3) | English | 8B-70B | base model<br>chat model |
411413
| Mistral<br>Mixtral | [Mistral series models](https://github.com/mistralai/mistral-src) | English | 7B-22B | base model<br>instruct model<br>MoE model |
412414
| YI | [01AI's YI series models](https://github.com/01-ai) | Chinese<br>English | 6B-34B<br>including quantized | base model<br>chat model<br>long text model |
413415
| InternLM<br>InternLM2<br>InternLM2-Math | [Pujiang AI Lab InternLM series models](https://github.com/InternLM/InternLM) | Chinese<br>English | 1.8B-20B | base model<br>chat model<br>math model |

‎README_CN.md‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,10 +40,11 @@ SWIFT支持近**200种LLM和MLLM**（多模态大模型）的训练、推理、
4040
此外，我们也在拓展其他模态的能力，目前我们支持了AnimateDiff的全参数训练和LoRA训练。
4141

4242
## 🎉 新闻
43+
- 2024.04.19: 支持**Llama3**系列模型的推理, 微调和部署等. 包括: Llama-3-8B, Llama-3-8B-Instruct, Llama-3-70B, Llama-3-70B-Instruct. 使用[这个脚本](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/llama3_8b_instruct/lora/sft.sh)开始训练叭！
4344
- 2024.04.18: 支持模型: wizardlm2-7b-awq, wizardlm2-8x22b, yi-6b-chat-awq, yi-6b-chat-int8, yi-34b-chat-awq, yi-34b-chat-int8. 支持`--deepspeed zero3-offload`, 提供了默认zero3-offload配置文件来使用zero3+cpu offload.
4445
- 2024.04.18: 支持使用环境变量`USE_HF`兼容HuggingFace生态, 切换成使用HF中的模型和数据集, 可以查看[HuggingFace生态兼容文档](https://github.com/modelscope/swift/tree/main/docs/source/LLM/HuggingFace生态兼容.md).
4546
- 2024.04.17: 支持OpenAI样式的接口评测, 可以查看[评测参数接口文档](docs/source/LLM/命令行参数.md#eval参数)来查看使用方法.
46-
- 🔥2024.04.17: 支持 **CodeQwen1.5-7B**系列: CodeQwen1.5-7B, CodeQwen1.5-7B-Chat,CodeQwen1.5-7B-Chat-AWQ, 使用[这个脚本](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/codeqwen1half_7b_chat/lora/sft.sh)来开始训练！
47+
- 🔥2024.04.17: 支持 **CodeQwen1.5-7B**系列: CodeQwen1.5-7B, CodeQwen1.5-7B-Chat, CodeQwen1.5-7B-Chat-AWQ, 使用[这个脚本](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/codeqwen1half_7b_chat/lora/sft.sh)来开始训练！
4748
- 2024.04.16: 支持llava-v1.6-34b的推理与微调, 最佳实践可以查看[这里](https://github.com/modelscope/swift/tree/main/docs/source/Multi-Modal/llava最佳实践.md).
4849
- 2024.04.13: 支持Mixtral-8x22B-v0.1模型的推理与微调, 使用[这个脚本](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/mixtral_moe_8x22b_v1/lora_ddp_ds/sft.sh)来开始训练！
4950
- 2024.04.13: 支持新推出的**MiniCPM**系列: MiniCPM-V-2.0、MiniCPM-2B-128k、MiniCPM-MoE-8x2B和MiniCPM-1B。使用[这个脚本](https://github.com/modelscope/swift/blob/main/examples/pytorch/llm/scripts/minicpm_moe_8x2b/lora_ddp/sft.sh)来开始训练！
@@ -405,6 +406,7 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
405406
| Yuan2 | [浪潮源系列模型](https://github.com/IEIT-Yuan) | 中文<br>英文 | 2B-102B | instruct模型 |
406407
| XVerse | [元象系列模型](https://github.com/xverse-ai) | 中文<br>英文 | 7B-65B | base模型<br>chat模型<br>长文本模型<br>MoE模型 | |
407408
| LLaMA2 | [LLaMA2系列模型](https://github.com/facebookresearch/llama) | 英文 | 7B-70B<br>包含量化版本 | base模型<br>chat模型 |
409+
| LLaMA3 | [LLaMA3系列模型](https://github.com/meta-llama/llama3) | 英文 | 8B-70B | base模型<br>chat模型 |
408410
| Mistral<br>Mixtral | [Mistral系列模型](https://github.com/mistralai/mistral-src) | 英文 | 7B-8x22B | base模型<br>instruct模型<br>MoE模型 |
409411
| YI | [01AI的YI系列模型](https://github.com/01-ai) | 中文<br>英文 | 6B-34B<br>包含量化版本 | base模型<br>chat模型<br>长文本模型 |
410412
| InternLM<br>InternLM2<br>InternLM2-Math | [浦江实验室书生浦语系列模型](https://github.com/InternLM/InternLM) | 中文<br>英文 | 1.8B-20B | base模型<br>chat模型<br>数学模型 |

0 commit comments

Comments
 (0)