Edit model card

Model Card: Llama-3-8B-Instruct-corrected

This is an upload of Meta's Llama 3 8B instruct with a corrected generation_config.json introduced in this commit. The EOS on inference now includes <|eot_id|>

Other Information

The original folder was removed from this upload

Please look at README-llama.md for the original README.

Downloads last month
2
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference API
Input a message to start chatting with royallab/Llama-3-8B-Instruct-corrected.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.