dnotitia/
dna-r1:14b-fp32

74 7 months ago

Reasoning model distilled from DeepSeek-R1, enhanced with GRPO using supplementary reasoning datasets.

14b
... /
params
785189245a82 · 83B
{
"num_predict": 4096,
"stop": [
"<|im_end|>"
],
"temperature": 0.1,
"top_p": 0.9
}