RefinedNeuro/
RN_TR_R2:latest

2,890 3 months ago

RN_TR_R2 is a Turkish-language reasoning model fine-tuned from Turkish-Llama-8B using GRPO. It excels in STEM and cultural Q&A tasks, scoring 82.4% on benchmarks. Ideal for education-focused reasoning in Turkish.

tools
... /
params
6cf8135b1a3c · 126B
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
],
"temperature": 0.6,
"top_p": 0.1
}