metadata
license: other
license_name: bsd-3-clause
license_link: https://github.com/TencentARC/TimeLens/blob/main/LICENSE
language:
- en
tags:
- video-grounding
- temporal-grounding
- video-understanding
- qwen2-vl
- mlx
- mlx-my-repo
library_name: transformers
pipeline_tag: video-text-to-text
datasets:
- TencentARC/TimeLens-100K
- TencentARC/TimeLens-Bench
base_model: TencentARC/TimeLens-7B
JungleGym/TimeLens-7B-mlx-fp16
The Model JungleGym/TimeLens-7B-mlx-fp16 was converted to MLX format from TencentARC/TimeLens-7B using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("JungleGym/TimeLens-7B-mlx-fp16")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)