Views
No views yet
meta-llama/Llama-3.1-8B-Instruct that has been trained to detect and mitigate hallucinations in generated text.trust_remote_code=True when loading it.1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_name = "MathBite/self_corrective_llama_3.1_8B"
4tokenizer = AutoTokenizer.from_pretrained(model_name)
5
6model = AutoModelForCausalLM.from_pretrained(
7 model_name,
8 trust_remote_code=True
9)