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
  - llama-cpp
  - gguf-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

Hasso5703/Mistral-Small-24B-Instruct-2501-reasoning-Q8_0-GGUF

This model was converted to GGUF format from yentinglin/Mistral-Small-24B-Instruct-2501-reasoning using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Hasso5703/Mistral-Small-24B-Instruct-2501-reasoning-Q8_0-GGUF --hf-file mistral-small-24b-instruct-2501-reasoning-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Hasso5703/Mistral-Small-24B-Instruct-2501-reasoning-Q8_0-GGUF --hf-file mistral-small-24b-instruct-2501-reasoning-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Hasso5703/Mistral-Small-24B-Instruct-2501-reasoning-Q8_0-GGUF --hf-file mistral-small-24b-instruct-2501-reasoning-q8_0.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Hasso5703/Mistral-Small-24B-Instruct-2501-reasoning-Q8_0-GGUF --hf-file mistral-small-24b-instruct-2501-reasoning-q8_0.gguf -c 2048