423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-04 18:02:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] Support Intern-S1-mini (#8976)

Browse Source
This commit is contained in:
Haian Huang(深度眸) 2025-08-20 23:52:51 +08:00 committed by GitHub
parent 022a326ca4
commit 1664657d80
5 changed files with 30 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -118,6 +118,8 @@ Choose your path:
## Changelog
[25/08/20] We supported fine-tuning the **[Intern-S1-mini](https://huggingface.co/internlm/Intern-S1-mini)** models. See [PR #8976](https://github.com/hiyouga/LLaMA-Factory/pull/8976) to get started.
[25/08/06] We supported fine-tuning the **[GPT-OSS](https://github.com/openai/gpt-oss)** models. See [PR #8826](https://github.com/hiyouga/LLaMA-Factory/pull/8826) to get started.
[25/07/02] We supported fine-tuning the **[GLM-4.1V-9B-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)** model.
@ -277,6 +279,7 @@ Choose your path:
| [Index](https://huggingface.co/IndexTeam) | 1.9B | index |
| [InternLM 2-3](https://huggingface.co/internlm) | 7B/8B/20B | intern2 |
| [InternVL 2.5-3](https://huggingface.co/OpenGVLab) | 1B/2B/8B/14B/38B/78B | intern_vl |
| [InternLM/Intern-S1-mini](https://huggingface.co/internlm/) | 8B | intern_s1 |
| [Kimi-VL](https://huggingface.co/moonshotai) | 16B | kimi_vl |
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |

3
README_zh.md
View File

@ -120,6 +120,8 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
## 更新日志
[25/08/20] 我们支持了 **[Intern-S1-mini](https://huggingface.co/internlm/Intern-S1-mini)** 模型的微调。查看 [PR #8976](https://github.com/hiyouga/LLaMA-Factory/pull/8976) 以使用。
[25/08/06] 我们支持了 **[GPT-OSS](https://github.com/openai/gpt-oss)** 模型的微调。查看 [PR #8826](https://github.com/hiyouga/LLaMA-Factory/pull/8826) 以使用。
[25/07/02] 我们支持了 **[GLM-4.1V-9B-Thinking](https://github.com/THUDM/GLM-4.1V-Thinking)** 模型的微调。
@ -279,6 +281,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
| [Index](https://huggingface.co/IndexTeam) | 1.9B | index |
| [InternLM 2-3](https://huggingface.co/internlm) | 7B/8B/20B | intern2 |
| [InternVL 2.5-3](https://huggingface.co/OpenGVLab) | 1B/2B/8B/14B/38B/78B | intern_vl |
| [InternLM/Intern-S1-mini](https://huggingface.co/internlm/) | 8B | intern_s1 |
| [Kimi-VL](https://huggingface.co/moonshotai) | 16B | kimi_vl |
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |

11
src/llamafactory/data/template.py
View File

@ -1201,6 +1201,17 @@ register_template(
)
register_template(
name="intern_s1",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
format_assistant=StringFormatter(slots=["{{content}}<|im_end|>\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
stop_words=["<|im_end|>"],
mm_plugin=get_mm_plugin(name="intern_vl", image_token="<image>", video_token="<video>"),
)
# copied from qwen template
register_template(
name="keye_vl",

10
src/llamafactory/extras/constants.py
View File

@ -1264,6 +1264,16 @@ register_model_group(
multimodal=True,
)
register_model_group(
models={
"Intern-S1-mini": {
DownloadSource.DEFAULT: "internlm/Intern-S1-mini",
DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/Intern-S1-mini",
}
},
template="intern_s1",
multimodal=True,
)
register_model_group(
models={

3
src/llamafactory/model/model_utils/visual.py
View File

@ -234,6 +234,9 @@ _register_composite_model(
model_type="internvl",
)
_register_composite_model(
model_type="interns1",
)
_register_composite_model(
model_type="Keye",