PRASSANT/xVyasa

Vyasa-Architect-3B

A 3B-parameter language model fine-tuned for architectural reasoning — converting natural language app descriptions into complete, structured Architectural Graph JSON.

Named after Vyasa (व्यास), the sage who conceived the entire Mahabharata completely in his mind before manifesting a single word.

Model Description

• Base Model: Qwen-2.5-3B-Instruct (4-bit quantized)
• Fine-tuning Method: QLoRA (LoRA rank 8, 8 layers, 3.33M trainable params)
• Training Data: 167 (intent → Architectural Graph) pairs generated by DeepSeek-V3
• Training Hardware: Apple M1 Pro, 32GB unified memory
• Training Duration: ~1 hour, 300 iterations
• Training Loss: 0.063 (train), 0.124 (validation)

Intended Use

This model is the Stage 1 (Conception) component of the Vyasa Manifestation Engine. It receives a natural language app description and produces a complete Architectural Graph JSON. This graph is then validated by a deterministic Witness (7 structural checks) and compiled to working code files by the Manifest Engine (deterministic Next.js/Prisma/TypeScript compiler).

The model does NOT generate code directly. It generates architectural specifications. Code is produced deterministically by the compiler.

Performance

Metric	Base Qwen-2.5-3B	Vyasa-Architect-3B
Valid JSON rate	0%	~50%
Witness-clean rate	0%	~25%

After simple SFT on 167 examples. GRPO+Witness reward training (in progress) targets 90%+ clean rate.

Usage

from mlx_lm import load, generate

model, tokenizer = load(
    "mlx-community/Qwen2.5-3B-Instruct-4bit",
    adapter_path="prashantpandey/vyasa-architect-3b"
)

prompt = "Conceive the complete architecture for: A todo app with tasks and categories"
response = generate(model, tokenizer, prompt=prompt, max_tokens=3000)

Architecture

Part of the Vyasa Manifestation Engine — a three-stage compiler architecture:

1. Conception (this model): Intent → Architectural Graph
2. Witness (deterministic): Validates structural integrity
3. Manifest (deterministic): Compiles graph to code files

Limitations

• ~50% valid JSON rate (GRPO training in progress to reach 90%+)
• Output is verbose (8K-11K chars per graph)
• Slow on CPU (~200 chars/sec); optimized for GPU inference
• Trained for Next.js/Prisma stack output; graph format is stack-agnostic

Citation

If you use this model, please cite:

@misc{vyasa-architect-3b,
  author = {Prashant Pandey},
  title = {Vyasa-Architect-3B: Architectural Reasoning via Structured Intermediate Representation},
  year = {2026},
  url = {https://github.com/prashantpandey-creator/puranic-architecture-paper}
}

License

This adapter is proprietary. All rights reserved. The base model (Qwen-2.5-3B) is Apache 2.0.