README.md

metadata

license: apache-2.0
datasets:
  - open-r1/OpenR1-Math-220k
  - yentinglin/s1K-1.1-trl-format
  - simplescaling/s1K-1.1
language:
  - en
metrics:
  - accuracy
base_model: yentinglin/Mistral-Small-24B-Instruct-2501-reasoning
pipeline_tag: text-generation
tags:
  - reasoning
  - mlx
  - mlx-my-repo
model-index:
  - name: yentinglin/Mistral-Small-24B-Instruct-2501-reasoning
    results:
      - task:
          type: text-generation
        dataset:
          name: MATH-500
          type: MATH
        metrics:
          - type: pass@1
            value: 0.95
            name: pass@1
            verified: false
        source:
          url: >-
            https://huggingface.co/spaces/yentinglin/zhtw-reasoning-eval-leaderboard
          name: yentinglin/zhtw-reasoning-eval-leaderboard
      - task:
          type: text-generation
        dataset:
          name: AIME 2025
          type: AIME
        metrics:
          - type: pass@1
            value: 0.5333
            name: pass@1
            verified: false
          - type: pass@1
            value: 0.6667
            name: pass@1
            verified: false
        source:
          url: >-
            https://huggingface.co/spaces/yentinglin/zhtw-reasoning-eval-leaderboard
          name: yentinglin/zhtw-reasoning-eval-leaderboard
      - task:
          type: text-generation
        dataset:
          name: GPQA Diamond
          type: GPQA
        metrics:
          - type: pass@1
            value: 0.62022
            name: pass@1
            verified: false
        source:
          url: >-
            https://huggingface.co/spaces/yentinglin/zhtw-reasoning-eval-leaderboard
          name: yentinglin/zhtw-reasoning-eval-leaderboard

johnjadensmith112/Mistral-Small-24B-Instruct-2501-reasoning-Q4-mlx

The Model johnjadensmith112/Mistral-Small-24B-Instruct-2501-reasoning-Q4-mlx was converted to MLX format from yentinglin/Mistral-Small-24B-Instruct-2501-reasoning using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("johnjadensmith112/Mistral-Small-24B-Instruct-2501-reasoning-Q4-mlx")

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)