Edit model card

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"

or

./llama-server --hf-repo NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF --hf-file latxa-7b-v1.2-q8_0.gguf -c 2048
Downloads last month
601
GGUF
Model size
6.74B params
Architecture
llama
Inference Examples
Unable to determine this model's library. Check the docs .

Quantized from

Dataset used to train NikolayKozloff/latxa-7b-v1.2-Q8_0-GGUF

Evaluation results

  • Accuracy (0-shot) on xstory_cloze
    Paper
    65.720
  • Accuracy (5-shot) on belebele
    Paper
    36.890
  • Average scores (5-shot) on basque_glue
    Paper
    51.780
  • Accuracy (5-shot) on eus_proficiency
    Paper
    32.440
  • Accuracy (5-shot) on eus_reading
    Paper
    30.400
  • Accuracy (5-shot) on eus_trivia
    Paper
    44.370
  • Accuracy (5-shot) on eus_exams
    Paper
    34.200