Hugging Face's logo

meta-llama
/
Llama-3.2-11B-Vision-Instruct

Image-Text-to-Text
Transformers
Safetensors
PyTorch
mllama
pretraining
facebook
meta
llama
llama-3
conversational
Inference Endpoints
Model card Files Community
38

Tokenizer needs to be fixed for BOS handling

#18
by dzhulgakov - opened
Discussion
dzhulgakov

Same issues as https://huggingface.co/nltpt/Llama-3.2-1B-Instruct/discussions/8 - raw encode() doesn't prepend BOS

Sign up or log in to comment