Biggie-SmoLlm-0.4B / README.md
nisten's picture
Create README.md
f22d98c verified
|
raw
history blame
420 Bytes

image/png

gguf file included , the model is surprisingly coherent in 8bit . Model itself still needs more training. Based off of SmolLM-360m

./llama-cli -ngl 99 -co --temp 0 -p "How to build a city on Mars via calculating Aldrin-Cycler orbits?" -m Biggie_SmolLM_400M_q8_0.gguf -cnv -fa --keep -1