ImFineThanks/ Integrator-1-R1-ZERO-3B:latest

63 1 year ago

It is an LLM fine-tuned from Llama-3.2-3B-Instruct, capable of reasoning in the format <reasoning>...</reasoning><answer>...</answer>. Its capability might improve with further training.

tools
... /
params
847df9147b57 · 127B
{
"num_ctx": 4096,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
],
"temperature": 0
}