Tanjiro comments

Results 27 comments of


                                            Tanjiro

Pose Estimation

I am GSSOC'21 Participant. Can you assign me this issue?

Pose Estimation

PR Generated #64

Chunked context incomplete outputs

Any updates on this, I am also facing the same buffer size issue

How to fix incomplete answers?

I have corrected this by replacing my stop token to None.

Medusa convert cpt doesn't work with safetensors version

Opened a PR #1535 for this

Medusa convert cpt doesn't work with safetensors version

@ncomly-nvidia kindly review this PR

Medusa convert cpt doesn't work with safetensors version

This has been merged, we can close this issue

Encountered an error in forward function: slice 712 exceeds buffer size 471

I am getting the same issue when trying speculative decoding (medusa) with vicuna, after some inference, it is getting buffer size exceeds 2560

Implement huggingface provider to support running open source models

I will take this up. @matankley assign it to me

Implement huggingface provider to support running open source models

Almost, done with implementation, during testing, I observed HuggingFace LLM unlike OpenAI models will be on the local system, which need to be initialized every time a function will run,...