Text Generation
Transformers
PyTorch
English
llama
Inference Endpoints
text-generation-inference

Upload 16 bit precision weights

#29
by mallorbc - opened

These weights are the full fp32. To save bandwidth and disk space, upload 16 bits.

These weights are the full fp32. To save bandwidth and disk space, upload 16 bits.

lol

These weights are the full fp32. To save bandwidth and disk space, upload 16 bits.

lol

What is funny about this?

These weights are the full fp32. To save bandwidth and disk space, upload 16 bits.

lol

What is funny about this?

I really don't think they are going to lower the quality just for someone but someone will upload a 16bit version of it at some point in time.

These weights are the full fp32. To save bandwidth and disk space, upload 16 bits.

lol

What is funny about this?

I really don't think they are going to lower the quality just for someone but someone will upload a 16bit version of it at some point in time.

Upload weights at different precisions. Or upload bf16

Sign up or log in to comment