rahilfahim/code-reviewer-lora

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/Llama-3.2-3B-Instruct-bnb-4bit",
    max_seq_length=2048,
    load_in_4bit=True,
)
model.load_adapter("rahilfahim/code-reviewer-lora")
FastLanguageModel.for_inference(model)

prompt = """### Instruction:
You are a Python code reviewer. Review the following code and identify bugs, style issues, and improvements.

### Input:
def add(a,b): return a+b

### Response:
"""

inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.3)
print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])