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 complete. Feel free to try it!~
Important Note: This was trained in the Alpaca format, so prompting should be something like:
### Instruction:
<system prompt> (without the <>, this works like telling the AI what it is/purpose. i.e. like ChatGPT API's system prompt)
### Input:
<prompt> (without the <>)
### Response:
Current upload: possibly final checkpoint
Benchmarks
wikitext2: Coming soon...
ptb-new: Coming soon...
c4-new: Coming soon...