From 4d3621e3d3c85bbd2f8f8864776f468957e97e90 Mon Sep 17 00:00:00 2001 From: Hertz <2267379130@qq.com> Date: Mon, 12 Jan 2026 01:15:00 +0800 Subject: [PATCH] [model] fixed&added Hunyuan models (#9750) --- README.md | 2 +- README_zh.md | 2 +- src/llamafactory/data/template.py | 2 +- src/llamafactory/extras/constants.py | 28 ++++++++++++++++++++++------ 4 files changed, 25 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index d1a43ac0b..72b35d336 100644 --- a/README.md +++ b/README.md @@ -291,7 +291,7 @@ Read technical notes: | [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 | | [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 | | [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 | diff --git a/README_zh.md b/README_zh.md index 757e097c4..17804be17 100644 --- a/README_zh.md +++ b/README_zh.md @@ -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-OSS](https://huggingface.co/openai) | 20B/120B | gpt_oss | | [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 | | [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 | diff --git a/src/llamafactory/data/template.py b/src/llamafactory/data/template.py index 751d9d39a..562f3375c 100644 --- a/src/llamafactory/data/template.py +++ b/src/llamafactory/data/template.py @@ -1139,7 +1139,7 @@ register_template( register_template( - name="hunyuan1_5", + name="hunyuan_small", format_user=StringFormatter(slots=["<｜hy_User｜>{{content}}<｜hy_place▁holder▁no▁8｜>"]), format_assistant=StringFormatter(slots=["{{content}}<｜hy_place▁holder▁no▁2｜>"]), format_system=StringFormatter(slots=["{{content}}<｜hy_place▁holder▁no▁3｜>"]), diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index e1803bf37..fdfaa46f2 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -1144,14 +1144,34 @@ register_model_group( register_model_group( 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": { DownloadSource.DEFAULT: "tencent/Hunyuan-7B-Instruct", - DownloadSource.MODELSCOPE: "AI-ModelScope/Hunyuan-7B-Instruct", + DownloadSource.MODELSCOPE: "Tencent-Hunyuan/Hunyuan-7B-Instruct", }, "Hunyuan-MT-7B-Instruct": { DownloadSource.DEFAULT: "tencent/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", ) @@ -1163,12 +1183,8 @@ register_model_group( DownloadSource.DEFAULT: "tencent/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="hunyuan1_5", + template="hunyuan_small", )