7 3 months ago

This model is Qwen4b-Instruct-2507 fine-tuned on ~13k Climsight data which are pairs of prompts/completions extracted from climsight pipeline. Below are all the technical specs of the fine-tuning process along with the evaluation used.

c19abce81d0d · 108B
{
"num_ctx": 24576,
"stop": [
"<|im_end|>",
"<|end_of_text|>"
],
"temperature": 0.6,
"top_p": 0.9
}