Llama-3.1-8B Code Reviewer

Official adapter · maintained by ModelForgeLab

Produces structured code review comments with severity ratings, rationale, and fix suggestions. Trained on annotated GitHub PR review data.

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-code-review")

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

• peft>=0.10
• transformers>=4.43
• vLLM