ertghiu256/ qwen3-4b-code-reasoning:latest

629 9 months ago

A small Qwen3 4 billion parameter model trained on nvidia/OpenCodeReasoning for coding tasks.

tools
... /
params
4a6ce91d86a8 · 99B
{
"repeat_penalty": 1,
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}