Llama v2 70b
dred0n opened this issue · comments
can you bring in the main exllama's support for 70b and cut a release please?
Give me a sec, will be done soon.
Wheels are uploaded: https://github.com/jllllll/exllama/releases/tag/0.0.7
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
dred0n opened this issue · comments
can you bring in the main exllama's support for 70b and cut a release please?
Give me a sec, will be done soon.
Wheels are uploaded: https://github.com/jllllll/exllama/releases/tag/0.0.7