Hugging Face's logo

meta-llama
/
Llama-3.1-8B-Instruct

Text Generation
Transformers
Safetensors
PyTorch
llama
facebook
meta
llama-3
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
158

what is the right tokenizer should I use for llama 3.1 8B?

#19
by calebl - opened
Discussion
calebl

what is the right tokenizer should I use for llama 3.1 8B?

kmtao

use meta-llama/Meta-Llama-3.1-8B-Instruct, tested on my machine.

Ksgk-fy

it seems that the apply_chat_template for the tokenizer is weird, it seems to add on extra assistant response indicator

Sign up or log in to comment