Research Index

Sovereign Technical Assets & Model Documentation

Technical documentation, architecture evaluations, open-weights parameters, and curated training corpora for the sovereign Forol-v1-Research model.

Open Weights & Corpora

Model Files & Dataset Repositories

Technical weights checkpoints, text tokenizers, and Indic regional data pipelines made accessible for academic research and integration audits.

Dataset Hub

Indic Text Corpus

A hand-curated Indic text dataset containing low-resource agricultural guides, medical pamphlets, and regional dialect conversations.

Access Repository

Model Weight

Forol-v1-Research

1.1B parameters decoders checkpoint. Grouped-query attention framework designed for efficient consumer RTX card inference.

Get Model Weights

API Integration

Tokenizer Setup

Vocabulary configuration (32,000 tokens) with native sub-word support for regional Marathi, Gujarati, and Hindi scripts.

Browse Python Setup

Technical Evaluation

Model Architecture Profile

Evaluated on low-compute configurations using standard consumer VRAM specifications.

Architectural Parameter Technical Metric Value Optimized Context Constraint
Active Parameters 1.1 Billion Grouped-Query Attention (GQA)
Context Window Constraint 8,192 Tokens Rotary Position Embeddings (RoPE)
Regional Sowing Advisory Accuracy 42.5 BLEU Evaluated against Saurashtra agronomy vectors
Inference Token Latency 15ms / token Calculated on consumer RTX 3060 (12GB)
Minimum Compute Requirement 4.2 GB VRAM Quantized INT4 weights profile

Prototype Research

Additional Guides & Experiments

Ongoing explorations and engineering references from the Forol research team.

Developer Guide

Integration Quickstart

A code reference for local loading, tensor allocation, and basic chat completions using the HuggingFace transformers module.

Open repository code →

Model Safety

Alignment Guardrails

Explore our safety evaluation frameworks, baseline prompt alignments, and vulnerability testing scores.

Open safety policies →

MCP Server

Dumb2Smart MCP Server

A Model Context Protocol server that enhances small/weak model outputs into optimized, higher-quality responses — designed to make compact LLMs viable for production.

In Research / Prototype Follow development →

Engineering Logs

Tuning Research Logs

Updates on tokenization changes, dataset pruning experiments, and loss convergence tracking details.

Read research logs →