Skip to content
ModelListedExternal
Download

F 16

Official model release of Improving LLM Video Understanding with 16 Frames Per Second

Sourcehuggingface.co/tsinghua-ee/F-16/tree/be2c02086f5294fcf89b9578ef99405188487d55
KindText modelBase modelQwen/Qwen2-7BVersionBgrade

Model source

Kind
Text model
File size
17.3 GB
Base model
Qwen/Qwen2-7B
Version
vall_parameters
Updated
Oct 30, 2026
Downloads
18
Source
Hugging Face

Source description

Improving LLM Video Understanding with 16 Frames Per Second

Official model release of Improving LLM Video Understanding with 16 Frames Per Second

Sources

1 source
Hugging FacePrimaryVersion be2c02086f5294fcf89b9578ef99405188487d55
huggingface.co/tsinghua-ee/F-16/tree/be2c02086f5294fcf89b9578ef99405188487d55

Verified Oct 30

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

all_parameters.bin

bin · 17.3 GB · SHA-256 db59feaa6089…f70c · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 14huggingface.co/tsinghua-ee/F-16

--- license: apache-2.0 datasets: - lmms-lab/LLaVA-Video-178K - ShareGPT4Video/ShareGPT4Video language: - en metrics: - accuracy base_model: - Qwen/Qwen2-7B - lmms-lab/llava-onevision-qwen2-7b-ov pipeline_tag: video-text-to-text library_name: transformers --- # Improving LLM Video Understanding with 16 Frames Per Second Official model release of [Improving LLM Video Understanding with 16 Frames Per Second](https://github.com/bytedance/F-16/)

NoteOct 30huggingface.co/tsinghua-ee/F-16

Source context: 18 downloads · 0 likes · Pipeline video-text-to-text · Library transformers · Repo tsinghua-ee/F-16

NoteAug 14huggingface.co/tsinghua-ee/F-16

Source context: 23 downloads · 0 likes · Pipeline video-text-to-text · Library transformers · Repo tsinghua-ee/F-16