Llama 3.1 8B Bash Scripting

Published by @shellcraft_ai · Community adapter

code #bash #shell #linux #devops #scripting

Bash scripting assistant with POSIX portability awareness. Generates robust scripts with error handling, argument parsing, logging, and safe temporary file usage.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/llama31-8b-bash-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

transformers>=4.43
vLLM

code public

Llama 3.1 8B Code Refactor

meta-llama/Meta-Llama-3.1-8B-Instruct