Video-Text-to-Text
Transformers
Safetensors
MLX
English
qwen2_5_vl
image-text-to-text
video-grounding
temporal-grounding
video-understanding
qwen2-vl
mlx-my-repo
text-generation-inference
4-bit precision
Instructions to use JungleGym/TimeLens-7B-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JungleGym/TimeLens-7B-mlx-4Bit with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JungleGym/TimeLens-7B-mlx-4Bit") model = AutoModelForMultimodalLM.from_pretrained("JungleGym/TimeLens-7B-mlx-4Bit", device_map="auto") - MLX
How to use JungleGym/TimeLens-7B-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download JungleGym/TimeLens-7B-mlx-4Bit --local-dir TimeLens-7B-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download generation_config.json from JungleGym/TimeLens-7B-mlx-4Bit: direct link, hf CLI and curl.
- Browser
- Download file 244 Bytes
-
https://huggingface.co/JungleGym/TimeLens-7B-mlx-4Bit/resolve/main/generation_config.json
- Command line
-
hf download hf://JungleGym/TimeLens-7B-mlx-4Bit/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/JungleGym/TimeLens-7B-mlx-4Bit/resolve/main/generation_config.json
244 Bytes
| { | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.05, | |
| "temperature": 0.1, | |
| "top_k": 1, | |
| "top_p": 0.001, | |
| "transformers_version": "4.51.3" | |
| } | |