julienp79/ occitan-gemma-3-4b-it-dora-sfttrainer:Q2_K

1 yesterday

Gemma 3 4B Instruct fine-tuned on Occitan via DoRA (r=16). Lightweight model for resource-constrained setups. Q2_K, Q4_K_M, Q5_K_M, Q8_0, f16.

... /
params
fa52478aa8bb · 93B
{
"num_ctx": 768,
"stop": [
"<end_of_turn>"
],
"temperature": 0.7,
"top_k": 64,
"top_p": 0.95
}