abandonedmonk/TinyLlama-1.1B-NL2SH-Alpaca-v1

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the model and tokenizer
model_name = "abandonedmonk/TinyLlama-1.1B-NL2SH-Alpaca"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda")

# Inference helper
def generate_command(model, tokenizer, instruction, inp=""):
    # build prompt in Alpaca-style
    prompt = f"""Instruction: {instruction}
Input: {inp}
Response:
"""
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        do_sample=False,    # greedy decoding
        temperature=0.0,
        num_return_sequences=1
    )
    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    # Extract the first line (command) after "Response:"
    # If you want to keep all the commands, just simply return 'generated_text' instead of 'response'
    response = generated_text.strip().split("Response:")[-1].strip().split('\n')[0]
    return response

# Example usage
instruction = "Rename all files with .andnav extension to .tile"
bash_cmd = generate_command(model, tokenizer, instruction)
print("Generated bash command:", bash_cmd)

@misc{vonwerra2022trl,
  title        = {{TRL: Transformer Reinforcement Learning}},
  author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
  year         = 2020,
  journal      = {GitHub repository},
  publisher    = {GitHub},
  howpublished = {\url{https://github.com/huggingface/trl}}
}