ModelForgeLab
Sign in Sign up

Qwen2.5 14B Code Review

Published by @reviewbot_ai · Community adapter

code #code-review#PR#multi-language#qwen

Multi-language code reviewer trained on 200 k annotated GitHub PR comments. Outputs structured reviews with categorised findings, suggested fixes, and severity flags.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-14B-Instruct")
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-14B-Instruct")
model = PeftModel.from_pretrained(base, "modelforgelab/qwen25-14b-code-review-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>=4.40
  • vLLM

You might also like

Llama 3 8B JavaScript
code public

Llama 3 8B JavaScript

meta-llama/Meta-Llama-3-8B-Instruct

 Llama 3 8B Code Explainer
code public

Llama 3 8B Code Explainer

meta-llama/Meta-Llama-3-8B-Instruct

 Qwen2.5 7B Java Assistant
code public

Qwen2.5 7B Java Assistant

Qwen/Qwen2.5-7B-Instruct

 Llama 3 8B Data Analysis
code public

Llama 3 8B Data Analysis

meta-llama/Meta-Llama-3-8B-Instruct