# ExperimentLab AI ### Sovereign Physical Engineering Intelligence & Foundation Small Language Models [![GitHub](https://img.shields.io/badge/GitHub_Org-Vigyan--workstation-000000?style=flat&logo=github&logoColor=white)](https://github.com/Vigyan-workstation) [![Desktop Workstation](https://img.shields.io/badge/Flagship_Workstation-vigyan--pro_v4.0.0-18181b?style=flat&logo=linux&logoColor=white)](https://github.com/Vigyan-workstation/vigyan-pro) [![Discord](https://img.shields.io/badge/Discord-Experimentlab_Community-5865F2?style=flat&logo=discord&logoColor=white)](https://discord.com/invite/Jck3tD6mhf) [![License](https://img.shields.io/badge/License-PolyForm_Noncommercial_1.0.0-blue.svg?style=flat)](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} } ``` ---
Developed by ExperimentLab AI. Built for physical engineers who value sovereignty and mathematical precision.