Instructions to use neo-saket/vidya-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neo-saket/vidya-9b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="neo-saket/vidya-9b",
	filename="gguf/vidya-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use neo-saket/vidya-9b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neo-saket/vidya-9b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf neo-saket/vidya-9b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neo-saket/vidya-9b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf neo-saket/vidya-9b:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf neo-saket/vidya-9b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf neo-saket/vidya-9b:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf neo-saket/vidya-9b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neo-saket/vidya-9b:Q4_K_M

Use Docker

docker model run hf.co/neo-saket/vidya-9b:Q4_K_M

LM Studio
Jan
Ollama
How to use neo-saket/vidya-9b with Ollama:
```
ollama run hf.co/neo-saket/vidya-9b:Q4_K_M
```

Unsloth Studio

How to use neo-saket/vidya-9b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for neo-saket/vidya-9b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for neo-saket/vidya-9b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for neo-saket/vidya-9b to start chatting

How to use neo-saket/vidya-9b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf neo-saket/vidya-9b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "neo-saket/vidya-9b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use neo-saket/vidya-9b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf neo-saket/vidya-9b:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default neo-saket/vidya-9b:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use neo-saket/vidya-9b with Docker Model Runner:
```
docker model run hf.co/neo-saket/vidya-9b:Q4_K_M
```

Lemonade

How to use neo-saket/vidya-9b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neo-saket/vidya-9b:Q4_K_M

Run and chat with the model

lemonade run user.vidya-9b-Q4_K_M

List all available models

lemonade list

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

Vidya is a fine-tuned 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):

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

Usage

Ollama (recommended)

ollama run neosaket/vidya:9b "Explain Newton's second law with an example."

To suppress chain-of-thought reasoning, start the assistant turn with <think>\n\n</think>\n\n.

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("neo-saket/vidya-9b")
tokenizer = AutoTokenizer.from_pretrained("neo-saket/vidya-9b")

messages = [{"role": "user", "content": "Explain Newton's second law with an example."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.3)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Example Prompts

Misconception correction (NCERT Physics, Class 9)

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.

NEET Biology — Genetics

Distinguish between incomplete dominance and codominance. Give one example of each from the NCERT syllabus.

Model Details


Base model	Qwen/Qwen3.5-9B
Fine-tuning framework	Unsloth + HuggingFace TRL
LoRA rank	16 (DoRA + rsLoRA)
Context length	4096 tokens
Language	English / Hindi (Hinglish)
License	Apache 2.0

Files

File	Description
`model.safetensors`	Full BF16 weights (18 GB)
`gguf/model-Q4_K_M.gguf`	Quantized GGUF for Ollama/llama.cpp (5.3 GB)
`config.json`	Model configuration
`tokenizer.*`	Qwen3.5 tokenizer files

Model tree for neo-saket/vidya-9b

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(294)

this model

Evaluation results

Tutoring Quality (Gemini-as-judge)
self-reported

4.60/5.0

neo-saket
/

vidya-9b