metadata

base_model: weathermanj/Menda-3b-Optim-200
datasets:
  - gsm8k
language: en
library_name: transformers
license: other
tags:
  - qwen
  - grpo
  - instruct
  - fine-tuned
  - reasoning
  - 3b
  - menda
  - chat
  - transformers
  - llama-cpp
  - gguf-my-repo
model-index:
  - name: Menda-3b-Optim-200
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: ARC-Challenge
          type: arc-challenge
        metrics:
          - type: accuracy
            value: 50
            name: Accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BoolQ
          type: boolq
        metrics:
          - type: accuracy
            value: 80
            name: Accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag
          type: hellaswag
        metrics:
          - type: accuracy
            value: 40
            name: Accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (Overall)
          type: mmlu
        metrics:
          - type: accuracy
            value: 69.47
            name: Accuracy

mattritchey/Menda-3b-Optim-200-Q4_K_M-GGUF

This model was converted to GGUF format from weathermanj/Menda-3b-Optim-200 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 mattritchey/Menda-3b-Optim-200-Q4_K_M-GGUF --hf-file menda-3b-optim-200-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo mattritchey/Menda-3b-Optim-200-Q4_K_M-GGUF --hf-file menda-3b-optim-200-q4_k_m.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 mattritchey/Menda-3b-Optim-200-Q4_K_M-GGUF --hf-file menda-3b-optim-200-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo mattritchey/Menda-3b-Optim-200-Q4_K_M-GGUF --hf-file menda-3b-optim-200-q4_k_m.gguf -c 2048