Mistral-NeMo-Minitron-8B-Instruct

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Instruct")

# Use the prompt template
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
 ]
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(tokenized_chat, stop_strings=["<extra_id_1>"], tokenizer=tokenizer)
print(tokenizer.decode(outputs[0]))

from transformers import AutoTokenizer
from transformers import pipeline

tokenizer  = AutoTokenizer.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Instruct")

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="nvidia/Mistral-NeMo-Minitron-8B-Instruct")
pipe(messages, max_new_tokens=64, stop_strings=["<extra_id_1>"], tokenizer=tokenizer)