metadata

base_model: HiTZ/latxa-7b-v1.2
datasets:
  - HiTZ/latxa-corpus-v1.1
language:
  - eu
  - en
license: llama2
metrics:
  - accuracy
  - f1
  - perplexity
pipeline_tag: text-generation
tags:
  - llama-cpp
  - gguf-my-repo
model-index:
  - name: Latxa-7b-v1.2
    results:
      - task:
          type: multiple-choice
        dataset:
          name: xstory_cloze
          type: XStory
        metrics:
          - type: Accuracy (0-shot)
            value: 65.72
            name: Accuracy (0-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper
      - task:
          type: multiple-choice
        dataset:
          name: belebele
          type: Belebele
        metrics:
          - type: Accuracy (5-shot)
            value: 36.89
            name: Accuracy (5-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper
      - task:
          type: mix
        dataset:
          name: basque_glue
          type: BasqueGLUE
        metrics:
          - type: Average scores (5-shot)
            value: 51.78
            name: Average scores (5-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper
      - task:
          type: multiple_choice
        dataset:
          name: eus_proficiency
          type: EusProficiency
        metrics:
          - type: Accuracy (5-shot)
            value: 32.44
            name: Accuracy (5-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper
      - task:
          type: multiple_choice
        dataset:
          name: eus_reading
          type: EusReading
        metrics:
          - type: Accuracy (5-shot)
            value: 30.4
            name: Accuracy (5-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper
      - task:
          type: multiple_choice
        dataset:
          name: eus_trivia
          type: EusTrivia
        metrics:
          - type: Accuracy (5-shot)
            value: 44.37
            name: Accuracy (5-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper
      - task:
          type: multiple_choice
        dataset:
          name: eus_exams
          type: EusExams
        metrics:
          - type: Accuracy (5-shot)
            value: 34.2
            name: Accuracy (5-shot)
        source:
          url: https://arxiv.org/abs/2403.20266
          name: Paper

NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF

This model was converted to GGUF format from HiTZ/latxa-7b-v1.2 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 NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF --hf-file latxa-7b-v1.2-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF --hf-file latxa-7b-v1.2-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 NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF --hf-file latxa-7b-v1.2-q8_0.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF --hf-file latxa-7b-v1.2-q8_0.gguf -c 2048