# ExperimentLab AI
### Sovereign Physical Engineering Intelligence & Foundation Small Language Models
[](https://github.com/Vigyan-workstation)
[](https://github.com/Vigyan-workstation/vigyan-pro)
[](https://discord.com/invite/Jck3tD6mhf)
[](https://github.com/Vigyan-workstation/vigyan-pro/blob/main/LICENSE)
Pioneering sovereign edge intelligence, air-gapped engineering desktop runtimes, Sparse Mixture of Experts (MoE), and deterministic Computer Algebra System (SymPy CAS) verification.
---
## Mission & Architecture
**ExperimentLab AI** designs and trains foundation Small Language Models (SLMs) and sovereign desktop workstations specifically for **physical engineers, mathematicians, roboticists, and silicon designers**.
Traditional cloud language models hallucinate mathematical proofs, leak sensitive IP via telemetry, and require costly continuous token fees. ExperimentLab eliminates these barriers through a dual-engine architecture:
* **Zero Cloud Dependence**: 100% offline edge execution on local hardware with zero network egress.
* **Deterministic CAS Truth**: Neural natural-language reasoning verified through in-process SymPy Computer Algebra System AST kernels.
* **Edge-Optimized Architectures**: Sparse Mixture of Experts (MoE) and ternary 1.58-bit {-1, 0, +1} BitNet quantization running natively on standard consumer CPUs without requiring discrete GPUs.
---
## 4-Tier Public Model Catalog
```
┌────────────────────────────────────────────────────────────────────────┐
│ ExperimentLab Foundation Model & Runtime Architecture │
│ │
│ [Tier 1] Edge GGUF Runtimes (Vigyan-Models-GGUF for vigyan CLI) │
│ [Tier 2] Sparse Mixture of Experts & Ternary Quantization (MoE, QAT) │
│ [Tier 3] Dense Foundation STEM SLMs (32B Titan, 7B, 2B Edge) │
│ [Tier 4] Doctoral Domain Checkpoints (Silicon RTL, Math, BioMed) │
└────────────────────────────────────────────────────────────────────────┘
```
### Tier 1: Production Edge GGUF Runtimes
Optimized quantized weights engineered for the **[Vigyan Pro Desktop Workstation](https://github.com/Vigyan-workstation/vigyan-pro)** and CLI model management:
* **[`Experimentlab/Vigyan-Models-GGUF`](https://huggingface.co/Experimentlab/Vigyan-Models-GGUF)**: Verified `Q4_K_M` and `IQ3_M` quantized binaries for `vigyan-2b-reasoning`, `vigyan-2b-stem`, and `vigyan-7b-stem`. Executable on standard laptops with less than 4 GB RAM.
Pull directly via the Vigyan CLI:
```bash
vigyan model pull vigyan-2b-reasoning-q4_k_m.gguf
```
### Tier 2: Flagship Sparse Mixture of Experts (MoE) & Ternary Quantization
* **[`Experimentlab/Vigyan-1.5B-4x-MoE`](https://huggingface.co/Experimentlab/Vigyan-1.5B-4x-MoE)**: 4-expert routed Sparse MoE providing 7B-class STEM reasoning at 1.5B active parameter inference speed.
* **[`shreyansh12183/Vigyan-3B-4x-MoE`](https://huggingface.co/shreyansh12183/Vigyan-3B-4x-MoE)**: Top-1 routing multi-expert model calibrated for symbolic deduction.
* **[`shreyansh12183/vigyan-3b-1.58bit-qat`](https://huggingface.co/shreyansh12183/vigyan-3b-1.58bit-qat)**: Pure 1.58-bit {-1, 0, +1} ternary BitNet model trained via Quantization-Aware Training.
* **[`shreyansh12183/vigyan-2b-reasoning-grpo`](https://huggingface.co/shreyansh12183/vigyan-2b-reasoning-grpo)**: GRPO test-time reasoning SLM trained on mathematical and logical verification trees.
### Tier 3: Foundation STEM Dense SLMs
* **[`Experimentlab/Vigyan-AI-32B`](https://huggingface.co/Experimentlab/Vigyan-AI-32B)** & **[`Experimentlab/Vigyan-AI-32B-Titan-v1`](https://huggingface.co/Experimentlab/Vigyan-AI-32B-Titan-v1)**: Flagship 32B models for deep multi-step scientific deduction and formal derivations.
* **[`Experimentlab/Vigyan-7B-STEM-Instruct-v1`](https://huggingface.co/Experimentlab/Vigyan-7B-STEM-Instruct-v1)** & **[`Experimentlab/Shreyansh-STEM-AI-7B-Final`](https://huggingface.co/Experimentlab/Shreyansh-STEM-AI-7B-Final)**: 7B dense scientific reasoning models.
* **[`Experimentlab/Shreyansh-STEM-AI-2B-v3`](https://huggingface.co/Experimentlab/Shreyansh-STEM-AI-2B-v3)** & **[`Experimentlab/Shreyansh-STEM-AI-2B-v3-Distilled`](https://huggingface.co/Experimentlab/Shreyansh-STEM-AI-2B-v3-Distilled)**: Compact 2B parameter edge SLMs for battery-powered operation.
* **[`Experimentlab/Vigyan-2B-STEM-Instruct-v1`](https://huggingface.co/Experimentlab/Vigyan-2B-STEM-Instruct-v1)**: Instruction-tuned STEM canary model.
### Tier 4: Doctoral & Domain-Specialized Intelligence
* **[`Experimentlab/olmo2-7b-silicon-rtl-eda`](https://huggingface.co/Experimentlab/olmo2-7b-silicon-rtl-eda)**: Hardware silicon specialist for synthesizable IEEE 1364 Verilog RTL, finite state machines, and synchronous timing circuits.
* **[`Experimentlab/olmo2-7b-phd-pure-math`](https://huggingface.co/Experimentlab/olmo2-7b-phd-pure-math)**: Pure mathematics, formal topology, real analysis, and abstract algebra.
* **[`Experimentlab/olmo2-7b-biomed-chem`](https://huggingface.co/Experimentlab/olmo2-7b-biomed-chem)**: Deep biochemistry, enzyme kinetics, and molecular thermodynamics.
* **[`Experimentlab/olmo2-7b-astro-logic`](https://huggingface.co/Experimentlab/olmo2-7b-astro-logic)**: Orbital mechanics, Hohmann transfers, and astrophysical dynamics.
* **[`Experimentlab/Vidhi-AI-Instruct`](https://huggingface.co/Experimentlab/Vidhi-AI-Instruct)**: Sovereign Indian legal intelligence aligned with the Bharatiya Nyaya Sanhita (BNS).
### Open Research Corpora & Datasets
* **[`Experimentlab/vigyan-ai-research-papers`](https://huggingface.co/datasets/Experimentlab/vigyan-ai-research-papers)**: Scientific literature and verified technical preprints.
* **[`shreyansh12183/shreyansh-1B-SLM-pretrain-stem-english`](https://huggingface.co/datasets/shreyansh12183/shreyansh-1B-SLM-pretrain-stem-english)**: 1 Billion token foundation pretraining corpus balanced for cold-start STEM intelligence.
* **[`shreyansh12183/shreyansh-hinglish-english-stem-500k`](https://huggingface.co/datasets/shreyansh12183/shreyansh-hinglish-english-stem-500k)**: 500,000 sample bilingual Hinglish-English dataset tailored for Indian engineering students.
---
## Community & Support
Join physical engineers, researchers, and autonomous agent builders on our official Discord server:
* **Discord Server**: **[Experimentlab Community](https://discord.com/invite/Jck3tD6mhf)** (65+ Members)
* **Key Channels**:
* `#announcements`: New model weights, benchmark scorecards, and research releases.
* `#workstation`: Vigyan Pro desktop installation, CLI model pulling, and setup support.
* `#research`: Model pretraining, MoE upcycling, and symbolic CAS evaluation.
* `#model-evals`: GSM8K, MATH, and Verilog synthesis test results.
---
## Legal, Intellectual Property & Non-Commercial Licensing
All models, quantized weights, pretraining datasets, research papers, and software released by ExperimentLab AI and Vigyan Workstation are strictly licensed under the **PolyForm Noncommercial License 1.0.0**:
* **Academic, Educational & Personal Research Use**: Freely permitted for students, academic researchers, university coursework, self-hosting, and civilian scientific inquiry.
* **AI Model Distillation Restriction (Section 8)**: You may not use any model outputs, weights, datasets, or documentation to train, fine-tune, distill, or evaluate competing artificial intelligence or foundation models without prior written enterprise authorization.
* **Trademark Protection (Section 9)**: No trademark, service mark, or brand rights in "ExperimentLab AI" or "Vigyan Pro" are granted.
* **Commercial Enterprise Licensing**: For commercial licensing, enterprise deployment, or OEM hardware distribution, contact **licensing@experimentlab.in**.
---
## Academic Attribution & Sovereign Citation
```bibtex
@article{singh2026vigyan,
title={Vigyan Sovereign Trilogy: Empirical Scaling Laws and Deterministic Symbolic-AST Evaluation of Edge Small Language Models},
author={Singh, Shreyansh},
institution={ExperimentLab AI Open Research},
year={2026},
url={https://github.com/Vigyan-workstation/vigyan-pro}
}
```
---