Hugging Face's logo

meta-llama
/
Meta-Llama-3-8B-Instruct

Text Generation
Transformers
Safetensors
PyTorch
English
llama
facebook
meta
llama-3
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
132

Changing "eos_token" to eot-id fix the issue of overflow of model response - at least using the Messages API.

#73
by myonlyeye - opened
base: refs/heads/main
←
from: refs/pr/73
Discussion Files changed
+1
-1
myonlyeye

Changing "eos_token" to eot-id fix the issue of overflow of model response - at least using the Messages API.

Changing "eos_token" to eot-id fix the issue of overflow of model response - at least using the Messages API.b070d1d2
Navanit-shorthills

https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/discussions/60
Its already raised here

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment