bumblebee
bumblebee copied to clipboard
elixir-nx
Pre-trained Neural Network models in Axon (+ 🤗 Models integration)
Ideally we should use any layer names we want and then have an explicit name/pattern mapping from hf/transformers names. This way we can keep the models consistent, and also share...
Currently there are some inputs applicable to most most models (input embeds, head mask, position ids), but not all models accept them. We should add the missing inputs to make...
A wrapper model that uses arbitrary encoder and decoder models. See [this example](https://huggingface.co/docs/transformers/model_doc/encoder-decoder#transformers.EncoderDecoderModel.forward.example).
Hello! As Speech to Text models such as Whisper are added having access to some of the impressive AI Text to Speech models would be a nice way to close...
It seems that bumblebee is not capable of loading Mixtral-8x7B models (base or instruct). I've checked the files and it should be able to load the model (in theory) since...
I'm working on adding LLaVA to bumblebee as a learning exercise. I need some guidance on a few things: 1. From the official implementation of LLaVA as seen [here](https://github.com/haotian-liu/LLaVA/blob/main/llava/model/multimodal_encoder/clip_encoder.py) ,...
Matches the LlamaCPP behavior. I finished the EBNF parser which encodes the grammar in the same way as the implementation from: https://github.com/huggingface/transformers/pull/27557 Unfortunately I think we may have to refactor...
A list of ideas to explore: * [x] Lazy transfers (so we don't load data into the GPU at once) * [x] FP16 on load * [x] FP16 policies on...
The main challenge is concurrent ASCII progress bars, perhaps we should show progress in a different way in that case. (Perhaps a single progress bar with accumulated info)