ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[model] support gemma3 (#7273)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-03-13 01:35:23 +08:00
committed by GitHub
parent e6159ad730
commit 4b9d8da5a4
9 changed files with 356 additions and 274 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
README_zh.md
View File

@@ -86,10 +86,10 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
### 最新模型的 Day-N 微调适配
| 适配时间 | 模型名称 |
| ------------ | ---------------------------------------------------------- |
| Day 0 | Qwen2.5 / Qwen2-VL / QwQ / QvQ / InternLM3 / MiniCPM-o-2.6 |
| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 |
| 适配时间 | 模型名称 |
| ------------ | ------------------------------------------------------------ |
| Day 0 | Qwen2.5 / Qwen2.5-VL / Gemma 3 / InternLM 3 / MiniCPM-o-2.6 |
| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 |
## 性能指标
@@ -108,6 +108,8 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 更新日志
[25/03/12] 我们支持了 **[Gemma-3](https://huggingface.co/blog/gemma3)** 模型的微调。
[25/02/24] 我们宣布开源 **[EasyR1](https://github.com/hiyouga/EasyR1)**，一个高效可扩展的多模态强化学习框架，支持高效的 GRPO 训练。
[25/02/11] 我们支持了在导出模型时保存 **[Ollama](https://github.com/ollama/ollama)** 配置文件。详细用法请参照 [examples](examples/README_zh.md)。
@@ -122,7 +124,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
[25/01/14] 我们支持了 **[MiniCPM-o-2.6](https://huggingface.co/openbmb/MiniCPM-o-2_6)** 和 **[MiniCPM-V-2.6](https://huggingface.co/openbmb/MiniCPM-V-2_6)** 模型的微调。 感谢 [@BUAADreamer](https://github.com/BUAADreamer) 的 PR.
[25/01/14] 我们支持了 **[InternLM3](https://huggingface.co/collections/internlm/)** 模型的微调。感谢 [@hhaAndroid](https://github.com/hhaAndroid) 的 PR。
[25/01/14] 我们支持了 **[InternLM 3](https://huggingface.co/collections/internlm/)** 模型的微调。感谢 [@hhaAndroid](https://github.com/hhaAndroid) 的 PR。
[25/01/10] 我们支持了 **[Phi-4](https://huggingface.co/microsoft/phi-4)** 模型的微调。
@@ -231,6 +233,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai) | 1.5B/7B/8B/14B/32B/70B/671B | deepseek3 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3 |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |
| [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - |
| [Granite 3.0-3.1](https://huggingface.co/ibm-granite) | 1B/2B/3B/8B | granite3 |