zhitels/UI-TARS-7B-DPO-8bit

This model was converted to MLX format from bytedance-research/UI-TARS-7B-DPO using mlx-vlm version 0.1.11. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm
python -m mlx_vlm.generate --model zhitels/UI-TARS-7B-DPO-8bit --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
31
Safetensors
Model size
2.2B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the HF Inference API does not support transformers models with pipeline type image-text-to-text