README.md

metadata

license: apache-2.0
language:
  - en
base_model: DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2
pipeline_tag: text-generation
tags:
  - merge
  - programming
  - code generation
  - code
  - codeqwen
  - moe
  - coding
  - coder
  - qwen2
  - chat
  - qwen
  - qwen-coder
  - mixture of experts
  - qwen2moe
  - 2X32B Shared.
  - shared expert
  - mlx
library_name: mlx

Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2-q4-mlx

This model Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2-q4-mlx was converted to MLX format from DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2 using mlx-lm version 0.25.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.2-q4-mlx")

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)