Tencent releases WeMM-Video-2B-FP8 checkpoint
Tencent released the WeMM-Video-2B-FP8 repository, an FP8 Block128 Safetensors variant of WeMM-Video-2B with 4.84 GiB of weights. The model supports text, image, audio, and video inputs and generates Chinese or English text responses; its listed capabilities come from Tencent’s model description. The repository documents successful loading and generation with Transformers 5.2.0 and patched vLLM 0.18.0 on an NVIDIA L20.
The release provides an open-weight, FP8-formatted checkpoint for joint audio-visual understanding and reasoning, making the model available for local loading and serving through documented Transformers and vLLM workflows.
tencent/WeMM-Video-2B-FP8 Video-Text-to-Text • 3B • Updated about 4 hours ago • 3 • 1
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text library_name: transformers base_model: tencent/WeMM-Video-2B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- fp8
WeMM-Video-2B · FP8 Block128
Overview
This repository contains the FP8 Block128 Safetensors variant of WeMM-Video-2B. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.
#Tencent#WeMM-Video-2B-FP8#WeMM-Video-2B#Transformers#vLLM#NVIDIA L20