Downloads · 30 days
0
VicUnlocked-alpaca-65b-QLoRA
Aeala/VicUnlocked-alpaca-65b-QLoRA
VicUnlocked-alpaca-65b-QLoRA is a machine learning model from Aeala. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Please note that this is a highly experimental LoRA model. It may do some good stuff, it might do some undesirable stuff. Training is paused for now. Feel free to try it!~
Access
Public
Updated Jun 4, 2023
Repo size
8 GB
Likes
16
Public
Repo makeup
Click a slice to open those files.
.bin1.6 GB · 100%
At a glance
- Access
- Public
- Created
- May 26, 2023
- Updated
- Jun 4, 2023
- SHA
- 9658e359
Datasets
Model card
From the Hugging Face model README
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 paused for 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: checkpoint of a retrain at ~1000 steps with fixed QLoRA repo. (6/4/2023)
Benchmarks
wikitext2: Coming soon...
ptb-new: Coming soon...
c4-new: Coming soon...
- Created
- May 26, 2023
- Updated
- Jun 4, 2023