from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import transformers
import torch

model_name = "jwnder/core42_jais-30b-chat-v3-bnb-4bit"

import warnings
warnings.filterwarnings('ignore')

tokenizer = AutoTokenizer.from_pretrained(model_input_folder, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_input_folder, trust_remote_code=True)

inputs = tokenizer("Testing LLM!", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True))