Christian Pala comments

Repositories
Issues
Comments

Results 6 comments of


                                            Christian Pala

Feature Request: add support for fine-tuned (Falcon) models

Hi! After converting the weights from the repository: OpenAssistant/falcon-7b-sft-top1-696, via hugging face, to the lit-parrot format, when I try generating, using base.py I get the following runtime size mismatch error:...

Complex beam search

Hi folks! Are there updates on constraint beam search? It's something we would like to integrate.

NVIDIA AMMO documentation

Hi folks! Are there updates on the docs?

Parameter --load_model_on_cpu is ignored by llama convert_checkpoint.py (version 0.9.0)

Same issue here.

Fail to build int4_awq on Mixtral 8x7b

Goog morning @nv-guomingz! We are also waiting for the fix. Cheers.

Fail to build int4_awq on Mixtral 8x7b

Hey folks, @Barry-Delaney @nv-guomingz is this still on the roadmap?