TheJoeZenOne
/

qwen-3b-reasoning

Model card Files Files and versions

qwen-3b-reasoning / README.md

TheJoeZenOne's picture

Trained with Unsloth

b2103b4 verified 10 months ago

|

history blame contribute delete

99 Bytes

	---
	license: apache-2.0
	base_model:
	- Qwen/Qwen2.5-VL-3B-Instruct
	tags:
	- unsloth
	- trl
	- grpo
	---