cnfusion's picture
Upload README.md with huggingface_hub
84ae348 verified
metadata
license: apache-2.0
datasets:
  - Tongyi-Zhiwen/DocQA-RL-1.6K
base_model: Tongyi-Zhiwen/QwenLong-L1-32B
tags:
  - long-context
  - large-reasoning-model
  - mlx
  - mlx-my-repo

cnfusion/QwenLong-L1-32B-mlx-3Bit

The Model cnfusion/QwenLong-L1-32B-mlx-3Bit was converted to MLX format from Tongyi-Zhiwen/QwenLong-L1-32B using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("cnfusion/QwenLong-L1-32B-mlx-3Bit")

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)