YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Model Info

Merge of my VicUnlocked-alpaca-half-30b LoRA

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:

Benchmarks

wikitext2: 4.372413635253906 ptb-new: 24.69171714782715 c4-new: 6.469308853149414

Results generated with GPTQ evals (not quantized) thanks to Neko-Institute-of-Science

Downloads last month
1,666
Safetensors
Model size
33B params
Tensor type
F32
Β·
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Aeala/VicUnlocked-alpaca-30b

Quantizations
2 models

Spaces using Aeala/VicUnlocked-alpaca-30b 36