README.md

metadata

base_model: unsloth/Qwen2.5-14B-Instruct-1M
language:
  - en
library_name: transformers
license: apache-2.0
tags:
  - unsloth
  - transformers
  - qwen
  - qwen2
  - mlx

bobig/Qwen2.5-14B-Instruct-1M-Q4

The Model bobig/Qwen2.5-14B-Instruct-1M-Q4 was converted to MLX format from unsloth/Qwen2.5-14B-Instruct-1M using mlx-lm version 0.21.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("bobig/Qwen2.5-14B-Instruct-1M-Q4")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)