from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")
model = AutoModelForCausalLM.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")

inputs = tokenizer(["Human: Hi, nice to meet you!\n\nAssistant: "], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=16)
print(tokenizer.batch_decode(outputs, skip_special_tokens=False))

output:

['Human: Hi, nice to meet you!\n\nAssistant: Hello. Great to meet you too. Well, how can I assist you today?<|endoftext|>']

RichardErkhov/heegyu_-_WizardVicuna-open-llama-3b-v2-4bits

Original model description:

RichardErkhov/
heegyu_-_WizardVicuna-open-llama-3b-v2-4bits