README.md

---
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: peft
license: apache-2.0
pipeline_tag: text-generation
tags:
- lora
- code-generation
- neural-architecture-search
- delta-nas
- pytorch
---

# Delta-NAS Mistral-7B-Instruct LoRA Adapter

This is a fully merged model (LoRA weights merged into base) for [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3), fine-tuned for **delta-based Neural Architecture Search (NAS)** — generating novel PyTorch image-classification architectures via unified code diffs.

## Model Description

This adapter is the result of 22 iterative fine-tuning cycles on the delta-NAS pipeline described in **"Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs"**. The model generates unified diffs that modify a baseline neural network architecture to produce new, functional PyTorch models.

### Training Details

- **Base model**: `mistralai/Mistral-7B-Instruct-v0.3`
- **Fine-tuning method**: LoRA (Low-Rank Adaptation)
- **LoRA rank (r)**: 16
- **LoRA alpha**: 32
- **LoRA dropout**: 0.05
- **Target modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
- **Training cycles**: 22 (iterative self-improvement)
- **Total trained candidates**: 733
- **Admitted novel architectures**: 68 (MinHash-Jaccard novelty filter + τ_acc ≥ 0.40)

### Evaluation Datasets

Models were evaluated on 6 LEMUR image-classification benchmarks:
- CIFAR-10, CIFAR-100, MNIST, SVHN, ImageNette, CelebA-Gender

### Key Results

| Metric | Value |
|--------|-------|
| Trained candidates | 733 |
| Valid rate (compiles + trains) | 66.4% |
| Mean 1-epoch accuracy | 50.0% (±8.1% SD across cycles) |
| ≥40% accuracy rate | 58.4% |
| Novel architectures admitted to LEMUR | 68 |

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "mistralai/Mistral-7B-Instruct-v0.3",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "ABrain/Delta-NAS-Mistral-7B")

# Generate a diff to modify a baseline architecture
prompt = """Given the following PyTorch neural network baseline:
[baseline code here]

Generate a unified diff that creates a novel architecture variant."""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Associated Resources

- **Code**: [ABrain-One/nn-gpt](https://github.com/ABrain-One/nn-gpt)
- **Generated models**: [ABrain-One/nn-dataset PR #204](https://github.com/ABrain-One/nn-dataset/pull/204) (197 del-* prefixed architectures)
- **Paper**: "Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs" (submitted to CVPR 2026)

## Citation

```bibtex
@article{deltanas2026,
  title={Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs},
  author={Adhikari, Santosh and Ignatov, Dmitry},
  year={2026}
}
```

## License

Apache 2.0 License (same as the base model)