From 9c0d033a15da97cdf10075beb7317f4ef6123791 Mon Sep 17 00:00:00 2001 From: Yaowei Zheng Date: Fri, 24 Oct 2025 13:22:36 +0800 Subject: [PATCH] [model] add qwen3vl 2b & 32b (#9343) --- README.md | 4 ++-- README_zh.md | 4 ++-- src/llamafactory/extras/constants.py | 16 ++++++++++++++++ 3 files changed, 20 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 23d06ae8..6d705680 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@ [![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors) [![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml) [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/) -[![Citation](https://img.shields.io/badge/citation-840-green)](https://scholar.google.com/scholar?cites=12620864006390196564) +[![Citation](https://img.shields.io/badge/citation-1000+-green)](https://scholar.google.com/scholar?cites=12620864006390196564) [![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags) [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai) @@ -317,7 +317,7 @@ Choose your path: | [Qwen2.5-Omni](https://huggingface.co/Qwen) | 3B/7B | qwen2_omni | | [Qwen3-Omni](https://huggingface.co/Qwen) | 30B | qwen3_omni | | [Qwen2-VL/Qwen2.5-VL/QVQ](https://huggingface.co/Qwen) | 2B/3B/7B/32B/72B | qwen2_vl | -| [Qwen3-VL](https://huggingface.co/Qwen) | 235B | qwen3_vl | +| [Qwen3-VL](https://huggingface.co/Qwen) | 2B/4B/8B/30B/32B/235B | qwen3_vl | | [Seed (OSS/Coder)](https://huggingface.co/ByteDance-Seed) | 8B/36B | seed_oss/seed_coder | | [Skywork o1](https://huggingface.co/Skywork) | 8B | skywork_o1 | | [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | diff --git a/README_zh.md b/README_zh.md index 4679663b..62f29ddc 100644 --- a/README_zh.md +++ b/README_zh.md @@ -5,7 +5,7 @@ [![GitHub contributors](https://img.shields.io/github/contributors/hiyouga/LLaMA-Factory?color=orange)](https://github.com/hiyouga/LLaMA-Factory/graphs/contributors) [![GitHub workflow](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml/badge.svg)](https://github.com/hiyouga/LLaMA-Factory/actions/workflows/tests.yml) [![PyPI](https://img.shields.io/pypi/v/llamafactory)](https://pypi.org/project/llamafactory/) -[![Citation](https://img.shields.io/badge/citation-840-green)](https://scholar.google.com/scholar?cites=12620864006390196564) +[![Citation](https://img.shields.io/badge/citation-1000+-green)](https://scholar.google.com/scholar?cites=12620864006390196564) [![Docker Pulls](https://img.shields.io/docker/pulls/hiyouga/llamafactory)](https://hub.docker.com/r/hiyouga/llamafactory/tags) [![Twitter](https://img.shields.io/twitter/follow/llamafactory_ai)](https://twitter.com/llamafactory_ai) @@ -319,7 +319,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc | [Qwen2.5-Omni](https://huggingface.co/Qwen) | 3B/7B | qwen2_omni | | [Qwen3-Omni](https://huggingface.co/Qwen) | 30B | qwen3_omni | | [Qwen2-VL/Qwen2.5-VL/QVQ](https://huggingface.co/Qwen) | 2B/3B/7B/32B/72B | qwen2_vl | -| [Qwen3-VL](https://huggingface.co/Qwen) | 235B | qwen3_vl | +| [Qwen3-VL](https://huggingface.co/Qwen) | 2B/4B/8B/30B/32B/235B | qwen3_vl | | [Seed (OSS/Coder)](https://huggingface.co/ByteDance-Seed) | 8B/36B | seed_oss/seed_coder | | [Skywork o1](https://huggingface.co/Skywork) | 8B | skywork_o1 | | [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index a5e05119..51ea9144 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -3197,6 +3197,10 @@ register_model_group( register_model_group( models={ + "Qwen3-VL-2B-Instruct": { + DownloadSource.DEFAULT: "Qwen/Qwen3-VL-2B-Instruct", + DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-2B-Instruct", + }, "Qwen3-VL-4B-Instruct": { DownloadSource.DEFAULT: "Qwen/Qwen3-VL-4B-Instruct", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-4B-Instruct", @@ -3205,6 +3209,10 @@ register_model_group( DownloadSource.DEFAULT: "Qwen/Qwen3-VL-8B-Instruct", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-8B-Instruct", }, + "Qwen3-VL-32B-Instruct": { + DownloadSource.DEFAULT: "Qwen/Qwen3-VL-32B-Instruct", + DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-32B-Instruct", + }, "Qwen3-VL-30B-A3B-Instruct": { DownloadSource.DEFAULT: "Qwen/Qwen3-VL-30B-A3B-Instruct", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-30B-A3B-Instruct", @@ -3221,6 +3229,10 @@ register_model_group( register_model_group( models={ + "Qwen3-VL-2B-Thinking": { + DownloadSource.DEFAULT: "Qwen/Qwen3-VL-2B-Thinking", + DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-2B-Thinking", + }, "Qwen3-VL-4B-Thinking": { DownloadSource.DEFAULT: "Qwen/Qwen3-VL-4B-Thinking", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-4B-Thinking", @@ -3229,6 +3241,10 @@ register_model_group( DownloadSource.DEFAULT: "Qwen/Qwen3-VL-8B-Thinking", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-8B-Thinking", }, + "Qwen3-VL-32B-Thinking": { + DownloadSource.DEFAULT: "Qwen/Qwen3-VL-32B-Thinking", + DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-32B-Thinking", + }, "Qwen3-VL-30B-A3B-Thinking": { DownloadSource.DEFAULT: "Qwen/Qwen3-VL-30B-A3B-Thinking", DownloadSource.MODELSCOPE: "Qwen/Qwen3-VL-30B-A3B-Thinking",