CatUkraine/Mistral-Instruct-Ukrainian-SFT-Q2_K-GGUF
This model was converted to GGUF format from Radu1999/Mistral-Instruct-Ukrainian-SFT
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 CatUkraine/Mistral-Instruct-Ukrainian-SFT-Q2_K-GGUF --model mistral-instruct-ukrainian-sft.Q2_K.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo CatUkraine/Mistral-Instruct-Ukrainian-SFT-Q2_K-GGUF --model mistral-instruct-ukrainian-sft.Q2_K.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-instruct-ukrainian-sft.Q2_K.gguf -n 128
- Downloads last month
- 286
Unable to determine this model’s pipeline type. Check the
docs
.
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard57.850
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard83.120
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard60.950
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard54.140
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.510
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard39.420