Video-Text-to-Text
MLX
Safetensors
English
qwen2_vl
apple-silicon
video-captioning
qwen2-vl
tarsier
4-bit precision
Instructions to use viavicdev/Tarsier2-Recap-7b-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use viavicdev/Tarsier2-Recap-7b-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download viavicdev/Tarsier2-Recap-7b-MLX-4bit --local-dir Tarsier2-Recap-7b-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
-
Model card: redact conversion recipe, correct sizes/usage, add measured example
Verified signature- Conversion section generalised; exact key remaps, failing handler, config reconstruction and convert command removed - Sizes corrected: weights 5.64 GB / repo 5.65 GB (was a single '~5.3 GB') - Usage fixed: generate() returns GenerationResult -> print(result.text) - Versions: verified on mlx-vlm 0.6.8 (was an unverified '0.6.3 or later') - Added measured example on CC0 test footage + note on packed 4-bit param count - base_model_relation: quantized set explicitlyd2df1d1
-
Upload README.md with huggingface_hub
Verified signature8f83edd -
Upload folder using huggingface_hub
Verified signature99d176c -
initial commit
Verified signature21d855b