423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2026-01-12 17:10:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] fixed&added Hunyuan models (#9750)

Browse Source
This commit is contained in:
Hertz
2026-01-12 01:15:00 +08:00
committed by GitHub
parent a296723697
commit 4d3621e3d3
4 changed files with 25 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -291,7 +291,7 @@ Read technical notes:
| [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - | | [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - |
| [GPT-OSS](https://huggingface.co/openai) | 20B/120B | gpt_oss | | [GPT-OSS](https://huggingface.co/openai) | 20B/120B | gpt_oss |
| [Granite 3-4](https://huggingface.co/ibm-granite) | 1B/2B/3B/7B/8B | granite3/granite4 | | [Granite 3-4](https://huggingface.co/ibm-granite) | 1B/2B/3B/7B/8B | granite3/granite4 |
| [Hunyuan/Hunyuan1.5 (MT)](https://huggingface.co/tencent/) | 1.8B/7B | hunyuan/hunyuan1_5 | | [Hunyuan/Hunyuan1.5 (MT)](https://huggingface.co/tencent/) | 0.5B/1.8B/4B/7B/13B | hunyuan/hunyuan_small |
| [InternLM 2-3](https://huggingface.co/internlm) | 7B/8B/20B | intern2 | | [InternLM 2-3](https://huggingface.co/internlm) | 7B/8B/20B | intern2 |
| [InternVL 2.5-3.5](https://huggingface.co/OpenGVLab) | 1B/2B/4B/8B/14B/30B/38B/78B/241B | intern_vl | | [InternVL 2.5-3.5](https://huggingface.co/OpenGVLab) | 1B/2B/4B/8B/14B/30B/38B/78B/241B | intern_vl |
| [Intern-S1-mini](https://huggingface.co/internlm/) | 8B | intern_s1 | | [Intern-S1-mini](https://huggingface.co/internlm/) | 8B | intern_s1 |

2
README_zh.md
View File

@@ -293,7 +293,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
| [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - | | [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - |
| [GPT-OSS](https://huggingface.co/openai) | 20B/120B | gpt_oss | | [GPT-OSS](https://huggingface.co/openai) | 20B/120B | gpt_oss |
| [Granite 3-4](https://huggingface.co/ibm-granite) | 1B/2B/3B/7B/8B | granite3/granite4 | | [Granite 3-4](https://huggingface.co/ibm-granite) | 1B/2B/3B/7B/8B | granite3/granite4 |
| [Hunyuan/Hunyuan1.5 (MT)](https://huggingface.co/tencent/) | 1.8B/7B | hunyuan/hunyuan1_5 | | [Hunyuan/Hunyuan1.5 (MT)](https://huggingface.co/tencent/) | 0.5B/1.8B/4B/7B/13B | hunyuan/hunyuan_small |
| [InternLM 2-3](https://huggingface.co/internlm) | 7B/8B/20B | intern2 | | [InternLM 2-3](https://huggingface.co/internlm) | 7B/8B/20B | intern2 |
| [InternVL 2.5-3.5](https://huggingface.co/OpenGVLab) | 1B/2B/4B/8B/14B/30B/38B/78B/241B | intern_vl | | [InternVL 2.5-3.5](https://huggingface.co/OpenGVLab) | 1B/2B/4B/8B/14B/30B/38B/78B/241B | intern_vl |
| [Intern-S1-mini](https://huggingface.co/internlm/) | 8B | intern_s1 | | [Intern-S1-mini](https://huggingface.co/internlm/) | 8B | intern_s1 |

2
src/llamafactory/data/template.py
View File

@@ -1139,7 +1139,7 @@ register_template(
register_template( register_template(
name="hunyuan1_5", name="hunyuan_small",
format_user=StringFormatter(slots=["<｜hy_User｜>{{content}}<｜hy_place▁holder▁no▁8｜>"]), format_user=StringFormatter(slots=["<｜hy_User｜>{{content}}<｜hy_place▁holder▁no▁8｜>"]),
format_assistant=StringFormatter(slots=["{{content}}<｜hy_place▁holder▁no▁2｜>"]), format_assistant=StringFormatter(slots=["{{content}}<｜hy_place▁holder▁no▁2｜>"]),
format_system=StringFormatter(slots=["{{content}}<｜hy_place▁holder▁no▁3｜>"]), format_system=StringFormatter(slots=["{{content}}<｜hy_place▁holder▁no▁3｜>"]),

28
src/llamafactory/extras/constants.py
View File

@@ -1144,14 +1144,34 @@ register_model_group(
register_model_group( register_model_group(
models={ models={
"Hunyuan-0.5B-Instruct": {
DownloadSource.DEFAULT: "tencent/Hunyuan-0.5B-Instruct",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-0.5B-Instruct",
},
"Hunyuan-1.8B-Instruct": {
DownloadSource.DEFAULT: "tencent/Hunyuan-1.8B-Instruct",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-1.8B-Instruct",
},
"Hunyuan-4B-Instruct": {
DownloadSource.DEFAULT: "tencent/Hunyuan-4B-Instruct",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-4B-Instruct",
},
"Hunyuan-7B-Instruct": { "Hunyuan-7B-Instruct": {
DownloadSource.DEFAULT: "tencent/Hunyuan-7B-Instruct", DownloadSource.DEFAULT: "tencent/Hunyuan-7B-Instruct",
DownloadSource.MODELSCOPE: "AI-ModelScope/Hunyuan-7B-Instruct", DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-7B-Instruct",
}, },
"Hunyuan-MT-7B-Instruct": { "Hunyuan-MT-7B-Instruct": {
DownloadSource.DEFAULT: "tencent/Hunyuan-MT-7B", DownloadSource.DEFAULT: "tencent/Hunyuan-MT-7B",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-MT-7B", DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-MT-7B",
}, },
"HY-MT1.5-7B-Instruct": {
DownloadSource.DEFAULT: "tencent/HY-MT1.5-7B",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/HY-MT1.5-7B",
},
"Hunyuan-A13B-Instruct": {
DownloadSource.DEFAULT: "tencent/Hunyuan-A13B-Instruct",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-A13B-Instruct",
},
}, },
template="hunyuan", template="hunyuan",
) )
@@ -1163,12 +1183,8 @@ register_model_group(
DownloadSource.DEFAULT: "tencent/HY-MT1.5-1.8B", DownloadSource.DEFAULT: "tencent/HY-MT1.5-1.8B",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/HY-MT1.5-1.8B", DownloadSource.MODELSCOPE: "Tencent-Hunyuan/HY-MT1.5-1.8B",
}, },
"HY-MT1.5-7B-Instruct": {
DownloadSource.DEFAULT: "tencent/HY-MT1.5-7B",
DownloadSource.MODELSCOPE: "Tencent-Hunyuan/HY-MT1.5-7B",
}, },
}, template="hunyuan_small",
template="hunyuan1_5",
) )