README.md

metadata

license: apache-2.0
base_model: DavidAU/Qwen2.5-Microsoft-NextCoder-Olympic-Instruct-FUSED-CODER-Fast-11B
language:
  - en
pipeline_tag: text-generation
tags:
  - merge
  - programming
  - code generation
  - code
  - codeqwen
  - coding
  - coder
  - qwen2
  - chat
  - qwen
  - qwen-coder
  - microsoft
  - nextcoder
  - selekt
  - code-generation
  - program-synthesis
  - evolutionary-algorithms
  - arc
  - arc-agi
  - soar
  - mlx
datasets:
  - microsoft/NextCoderDataset
  - microsoft/NextCoderDataset-Conversational
  - bigcode/commitpackft
  - bigcode/starcoderdata
library_name: mlx

Qwen2.5-Microsoft-NextCoder-Olympic-Instruct-FUSED-CODER-Fast-11B-q8-mlx

This model Qwen2.5-Microsoft-NextCoder-Olympic-Instruct-FUSED-CODER-Fast-11B-q8-mlx was converted to MLX format from DavidAU/Qwen2.5-Microsoft-NextCoder-Olympic-Instruct-FUSED-CODER-Fast-11B using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen2.5-Microsoft-NextCoder-Olympic-Instruct-FUSED-CODER-Fast-11B-q8-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)