noxinc/Mistral-portuguese-luana-7b-chat-Q5_K_M-GGUF
This model was converted to GGUF format from rhaymison/Mistral-portuguese-luana-7b-chat
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 noxinc/Mistral-portuguese-luana-7b-chat-Q5_K_M-GGUF --model mistral-portuguese-luana-7b-chat.Q5_K_M.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo noxinc/Mistral-portuguese-luana-7b-chat-Q5_K_M-GGUF --model mistral-portuguese-luana-7b-chat.Q5_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.
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m mistral-portuguese-luana-7b-chat.Q5_K_M.gguf -n 128
- Downloads last month
- 7
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.
Model tree for noxinc/Mistral-portuguese-luana-7b-chat-Q5_K_M-GGUF-PTBR
Base model
mistralai/Mistral-7B-Instruct-v0.2Dataset used to train noxinc/Mistral-portuguese-luana-7b-chat-Q5_K_M-GGUF-PTBR
Evaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard59.130
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard49.240
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard36.580
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard90.470
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard76.550
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard66.750
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard77.460
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard69.450
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard59.630