we1kkk
/

llama2-hf-qlora-oasst1

Text Generation

Model card Files Files and versions Community

llama2-hf-qlora-oasst1 / README.md

we1kkk's picture

Create README.md

729ed04 over 1 year ago

|

149 Bytes

	---
	datasets:
	- OpenAssistant/oasst1
	pipeline_tag: conversational
	---
	Lora weight for Llama2 trained on oasst1 dataset using 4bit quantazation QLoRA.