19 2 days ago

Vidya is a fine-tuned Qwen3.5-9B tutoring assistant for Indian students — NCERT Classes 6–12, IIT-JEE, and NEET — with step-by-step reasoning and misconception correction.

2b 4b 9b
ollama run neosaket/vidya:2b

Models

View all →

Readme

Vidya 4B/9B — NCERT / IIT-JEE / NEET Tutor

Vidya is a fine-tuned Qwen3.5-4B and Qwen3.5-9B model trained to be an expert tutoring assistant for Indian students covering:

  • NCERT curriculum, Classes 6–12 (Physics, Chemistry, Biology, Mathematics, Social Science)
  • IIT-JEE (Mains + Advanced) problem solving
  • NEET Biology, Chemistry, Physics

Tutoring quality score: 4.60 / 5.0 (Gemini-as-judge, evaluated on misconception correction and step-by-step reasoning)

## Training Pipeline

Fine-tuned via a 3-stage pipeline on an RTX 5090 (32 GB VRAM):

  1. CPT — Continued pre-training on NCERT textbook content
  2. SFT — Supervised fine-tuning on educational Q&A, exam problems, and tutoring conversations
  3. DPO — Alignment for pedagogically effective responses

## Usage

”`bash ollama run neosaket/vidya:9b “Explain Newton’s second law with an example.”

To suppress chain-of-thought reasoning:

ollama run neosaket/vidya:9b –nowordwrap

ollama run neosaket/vidya:4b –nowordwrap

# Start your message with \n\n\n\n

Example Prompts

Misconception correction (NCERT Physics)

▎ A student believes that if no force acts on an object, it must be at rest. How would you correct this?

IIT-JEE Electrostatics

▎ Two point charges +4 μC and −4 μC are placed 20 cm apart. Find the electric field at the midpoint between them.

NEET Neurophysiology

▎ Describe the sequence of events during an action potential, including the role of voltage-gated Na⁺ and K⁺ channels.

NCERT Class 12 Mathematics

▎ Differentiate f(x) = x² sin(x) with respect to x and simplify.

IIT-JEE Organic Chemistry

▎ Why does benzene undergo electrophilic substitution rather than addition? Explain using resonance and stability arguments.

Model Details

┌────────────────┬────────────────────────────┐ │ │ │ ├────────────────┼────────────────────────────┤ │ Base model │ Qwen/Qwen3.5-9B and 4B │ ├────────────────┼────────────────────────────┤ │ Quantization │ Q4_K_M (GGUF, 5.3 GB) │
├────────────────┼────────────────────────────┤ │ Context length │ 4096 tokens │ ├────────────────┼────────────────────────────┤ │ Language │ English / Hindi (Hinglish) │ ├────────────────┼────────────────────────────┤ │ License │ Apache 2.0 │ └────────────────┴────────────────────────────┘

Links

  • HuggingFace: neo-saket/vidya-9b
  • HuggingFace: neo-saket/vidya-4b