Issues
- 2
Bumblebee.apply_tokenizer fails for empty text
#373 opened by yujonglee - 2
Using bumblebee from git is broken
#372 opened by dennym - 4
Error loading gpt3.5 tokenizer
#371 opened by yujonglee - 1
llama3 requires 2 eos_token_id's
#367 opened by jkbbwr - 4
Support Mixtral
#365 opened by WebCloud - 5
Just download a model from HuggingFace?
#363 opened by lawik - 22
Stream audio chunk by chunk to Whisper
#261 opened by mat-hek - 1
Add support for "google/gemma-7b-it"
#357 opened by kurtome - 3
CUDA 12.2 support
#351 opened by lambdaofgod - 10
Support LLaVA
#273 opened by briankariuki - 1
- 2
- 2
Unknown error serving Llama 2 derivative model
#348 opened by brainlid - 1
- 0
Download sharded parameters in parallel
#258 opened by jonatanklosko - 1
Running Whisper using bf16 fails
#345 opened by costaraphael - 4
Parameter persistence with sharding support
#338 opened by jonatanklosko - 1
Token Classification error in Livebook
#343 opened by jkwchui - 2
- 2
Tied word embeddings
#339 opened by jonatanklosko - 0
Add annotations to QKV layers
#291 opened by seanmor5 - 0
Confidences/probabilities for Whisper results
#335 opened by zacharygraber - 9
Support returning token count information
#287 opened by brainlid - 2
Error when using TinyLlama
#325 opened by trickster - 10
Featurizer different from python?
#323 opened by sonic182 - 2
Weird behaviour with progress status.
#324 opened by hickscorp - 7
Model "Salesforce - Blip large" fails
#269 opened by ndrean - 2
`TextEmbedding` crashes when both Mean Pooling and `compile` opts is specified
#315 opened by thiagopromano - 3
Cannot use `whisper-*.en` models in bumblebee
#312 opened by John-Goff - 1
Improve the error message when Hugging Face resource isn't found a the referenced location.
#313 opened by meanderingstream - 0
- 2
Finetuning Whisper with Bumblebee / Axon
#265 opened by omarelb - 0
- 0
- 2
- 1
- 1
Support Starcoder Model
#279 opened by jonastemplestein - 1
Bumblebee fails to load gpt models in main.
#293 opened by ityonemo - 5
- 4
Halting Nx Serving streams with a stop token
#288 opened by zblanco - 0
Support temperature in generation options
#286 opened by jonatanklosko - 11
Support DeepSeek Coder Model
#278 opened by jonastemplestein - 2
Multimodal projected embeddings
#274 opened by lambadalambda - 1
"cannot perform operation across devices mps and cpu" when running examples with torchx and mps
#275 opened by lambadalambda - 8
- 4
How to load .en variants under recent versions?
#267 opened by lawik - 5
How do you deploy this on Fly.io?
#270 opened by ndrean - 7
Error running Stable Diffusion example
#266 opened by gordoneliel - 2
Will there be any support for LLaMa2 in the future?
#260 opened by sutgeorge - 2
Reducing entry barrier for Elixir ML - can we showcase bumblebee based elixir code exposed as REST api to integrate with other frameworks ?
#262 opened by insidesmart