code-reviewer-lora by Rahil Fahim: Open-Weight Model

Model Card

By Rahil Fahim, published under mit, revision b835c285734c.

A LoRA adapter fine-tuned with QLoRA on Llama 3.2 3B Instruct to review Python code with severity levels (Critical, Warning, Info). Trained using Unsloth on Google Colab.

Read Rahil Fahim's full model card

Code Reviewer LoRA — Llama 3.2 3B

A LoRA adapter fine-tuned with QLoRA on Llama 3.2 3B Instruct to review Python code with severity levels (Critical, Warning, Info).

Training Summary

Metric	Value
Base model	Llama 3.2 3B Instruct
Method	QLoRA (rank 16, alpha 16)
Training examples	500
Training time	2.5 min (Colab T4)
Final loss	0.11
Adapter size	88 MB

Usage

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])

Links

Full project: GitHub Repo
Live demo: HF Space
Benchmark: docs/benchmark_results.json

Acknowledgments

Trained using Unsloth on Google Colab.

Identity and Version

Repository: rahilfahim/code-reviewer-lora
Publisher: Rahil Fahim
Task: Text generation
Modality: Text
Library: peft
Parameters: Not stated by the source
Languages: en
Revision: b835c285734cf899d5105dd13d4cf1496100c2e4
First published: 2026-09-19
Last updated: 2026-09-20

Files and Weights

8 files, 114.6 MB in total. The weights are 1 file totalling 97.3 MB in safetensors.

Weights1 file · 97.3 MB

Configuration2 files · 1.8 KB

Tokenizer2 files · 17.3 MB

Documentation1 file · 1.8 KB

Other1 file · 3.8 KB

Repository1 file · 1.6 KB

Every file

File	Type	Size	SHA-256
adapter_model.safetensors	Weights	97.3 MB	474fa23aea9b
adapter_config.json	Configuration	1.3 KB	—
special_tokens_map.json	Configuration	454 B	—
README.md	Documentation	1.8 KB	—
chat_template.jinja	Other	3.8 KB	—
.gitattributes	Repository	1.6 KB	—
tokenizer.json	Tokenizer	17.2 MB	6b9e4e7fb171
tokenizer_config.json	Tokenizer	50.6 KB	—

License and Download

License: mit
Access: Open weights, no gate
Download size: 97.3 MB

Download from Rahil Fahim

Released by Rahil Fahim through its official repository on Hugging Face. Read the license.

Built From

Adapter of unsloth/Llama-3.2-3B-Instruct-bnb-4bit
Derived from unsloth/Llama-3.2-3B-Instruct-bnb-4bit

Memory Requirements

Precision	Weights in memory
As published	97.3 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About code-reviewer-lora

Can I use code-reviewer-lora commercially?

Yes. code-reviewer-lora is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Qwen3.8-27B-Uncensored-GGUF

Jonathan Coletti

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers

View model