RefinedNeuro/ qwen3.8-27b-noslop:q2_k_xl

4,515 5 days ago

Plain-spoken Qwen3.8-27B fine-tune: 42% less slop, 73% fewer em dashes, same coding-agent pass rate. MTP speculative decoding built in.

tools thinking
... /
params
4a72b8469c9f ยท 115B
{
"draft_num_predict": 4,
"min_p": 0,
"presence_penalty": 0,
"repeat_penalty": 1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
}