moesaif/
meer-whale-1:latest

11 2 months ago

Fine-tuned Gemma-based model for code, reasoning, and developer interaction. Compact, optimized for vLLM and llama.cpp.

... /
params
b65fb927fa64 · 97B
{
"num_ctx": 4096,
"num_thread": 8,
"stop": [
"<end_of_turn>"
],
"temperature": 0.6,
"top_p": 0.9
}