Ryan Ramos

Has anyone gotten this to work on Kaggle?

1

This isn't really an "issue" so I apologize in advance if this needs to be closed, but has anyone succesfully gotten this to work on Kaggle? I tried to get...

Hi, I'm trying to implement the consensus opinion (`levels_mean`) as a geometric mean of the top-down predictions, bottom-up predictions, attention-weighted average of same-level embeddings, and embeddings of the previous time...

Batch size changes inference

2

Issue should be reproducible with [this notebook](https://colab.research.google.com/drive/1nAz2MUphzg5ifWW3CfRCJdYUgSYN5ynH?usp=sharing). (rest is copied from [this issue](https://github.com/huggingface/transformers/issues/22861) but they can't help with `decapoda-research/llama-7b-hf` which I assume `alpaca-lora` is for) Basically when I run `generate`...

Baseball Reference has information on the state a starter left the game in when he was pulled (e.g. `8b --- 2 out a2` for 7.2 innings, bases empty, up by...

Support for half precision?

7

Are there any instructions on how to get this code working for half precision? If I'm not mistaken, `diffusers==0.3.0` might be problematic for this (I think the VAE couldn't handle...

Code for replicating FairFace experiments

1

Firstly, thank you for providing code for the rest of your experiments! May I ask if there are any plans to release code for replicating the FairFace results of the...

Differing copy-paste mechanics between tmux and non-tmux

3

## Description of the problem or steps to reproduce Could someone help me understand which of these is the expected behavior? When I ssh into my workstation, I can copy...

device_map="auto" leads to `Expected all tensors to be on the same device` error on generate call

1

### System Info ```Shell - `Accelerate` version: 0.27.0 - Platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35 - Python version: 3.11.5 - Numpy version: 1.26.4 - PyTorch version (GPU?): 2.3.0+cu121 (True) - PyTorch XPU available: False...

MM-Vet download link broken

2

The [download link](https://objects.githubusercontent.com/github-production-release-asset-2e65be/674424428/70d2c2c1-1833-461b-875e-ee3a6f903f72?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20240516%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240516T093527Z&X-Amz-Expires=300&X-Amz-Signature=26f8c01f47ef0754116687c16b650af513e93fa660be9ce47b45e95c5bd59f1d&X-Amz-SignedHeaders=host&actor_id=99701420&key_id=0&repo_id=674424428&response-content-disposition=attachment%3B%20filename%3Dmm-vet.zip&response-content-type=application%2Foctet-stream) for MM-Vet from this [part of the docs](https://tinyllava-factory.readthedocs.io/en/latest/Evaluation.html#mm-vet) seems to be down. Can I confirm if this [link](https://github.com/yuweihao/MM-Vet/releases/download/v1/mm-vet.zip) from the [LLaVA repo](https://github.com/haotian-liu/LLaVA/blob/main/docs/Evaluation.md#mm-vet) is the same thing?

Proper set-up for the plugin

1

I originally asked this in a different repo, but as advised it does make a lot more sense to ask this here Basically I:m having a hard time getting the...