metadata
datasets:
- gozfarb/ShareGPT_Vicuna_unfiltered
LoRA Info:
Please note that this is a highly experimental LoRA model. It may do some good stuff, it might do some undesirable stuff. Training is basically done now. Feel free to try it!~
Important Note: While this is trained on a cleaned ShareGPT dataset like Vicuna used, this was trained in the Alpaca format, so prompting should be something like:
### Instruction:
<prompt> (without the <>)
### Response:
Current upload: Fully trained adapter model (3 epochs).
Secondary upload: checkpoint of epoch 2.97 (of 3)
Thanks to MetaIX for initial seemingly successful testing of the first uploaded checkpoint (epoch 0.8) as well as epoch 1.
Wikitext2 eval benchmark for epoch 0.8 upload (4-bit merge): 4.548329830169678 (Thanks to Metal/MetaIX)