from transformers import AutoTokenizer, LlamaForCausalLM

model = LlamaForCausalLM.from_pretrained("otonomy/Cn_2_9_3_Hinglish_llama3_7b_8kAk")
tokenizer = AutoTokenizer.from_pretrained("otonomy/Cn_2_9_3_Hinglish_llama3_7b_8kAK")

prompt = "ky tumhe la la land pasand hai?"
inputs = tokenizer(prompt, return_tensors="pt")

# Generate
generate_ids = model.generate(inputs.input_ids, max_length=30)
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]

# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="otonomy/Cn_2_9_3_Hinglish_llama3_7b_8kAk")
pipe(messages)