Model: vihangd/DopeyTinyLlama-1.1B-v1 Source: Original Platform
license
| license |
|---|
| apache-2.0 |
DopeyTinyLlama-1.1B-v1
An experimental DPO finetune of SmarTinyLlama with Alpaca-QLoRADatasets
Trained on bagel style DPO datasetsPrompt Template
Uses chatml style prompt templateDescription