NikolayKozloff/gemma-portuguese-luana-2b-Q8_0-GGUF
This model was converted to GGUF format from rhaymison/gemma-portuguese-luana-2b 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.
brew install ggerganov/ggerganov/llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo NikolayKozloff/gemma-portuguese-luana-2b-Q8_0-GGUF --model gemma-portuguese-luana-2b.Q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo NikolayKozloff/gemma-portuguese-luana-2b-Q8_0-GGUF --model gemma-portuguese-luana-2b.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.
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m gemma-portuguese-luana-2b.Q8_0.gguf -n 128
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train NikolayKozloff/gemma-portuguese-luana-2b-GGUF
Evaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard24.420
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard24.340
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard27.110
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard70.860
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard1.510
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard43.970
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard40.050
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard51.830
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard30.420