Felladrin's picture
Update README.md
c98195f verified
|
raw
history blame
756 Bytes
metadata
license: apache-2.0
base_model: Felladrin/TinyMistral-248M-Chat-v2

GGUF version of Felladrin/TinyMistral-248M-Chat-v2.

Usage with llama.cpp

brew install ggerganov/ggerganov/llama.cpp
llama-cli \
  --hf-repo Felladrin/gguf-TinyMistral-248M-Chat-v2 \
  --model TinyMistral-248M-Chat-v2.Q8_0.gguf \
  -p "<|im_start|>system\nYou are a helpful assistant who answers user's questions with details and curiosity.<|im_end|>\n<|im_start|>user\nWhat are some potential applications for quantum computing?<|im_end|>\n<|im_start|>assistant\n" \
  -e \
  --dynatemp-range "0.1-0.35" \
  --min-p 0.05 \
  --repeat-penalty 1.1 \
  -c 2048 \
  -n 250 \
  -r "<|im_end|>"