TencentARC/TimeLens-Bench
Viewer • Updated • 2.32k • 835 • 3
How to use JungleGym/TimeLens-7B-mlx-fp16 with Transformers:
# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText
processor = AutoProcessor.from_pretrained("JungleGym/TimeLens-7B-mlx-fp16")
model = AutoModelForImageTextToText.from_pretrained("JungleGym/TimeLens-7B-mlx-fp16")How to use JungleGym/TimeLens-7B-mlx-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir TimeLens-7B-mlx-fp16 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.
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)
Quantized