Instructions to use Abbas8910/Shiksha-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abbas8910/Shiksha-AI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Abbas8910/Shiksha-AI",
	filename="Shiksha_AI.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Abbas8910/Shiksha-AI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abbas8910/Shiksha-AI
# Run inference directly in the terminal:
llama-cli -hf Abbas8910/Shiksha-AI

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abbas8910/Shiksha-AI
# Run inference directly in the terminal:
llama-cli -hf Abbas8910/Shiksha-AI

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 Abbas8910/Shiksha-AI
# Run inference directly in the terminal:
./llama-cli -hf Abbas8910/Shiksha-AI

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 Abbas8910/Shiksha-AI
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abbas8910/Shiksha-AI

Use Docker

docker model run hf.co/Abbas8910/Shiksha-AI

LM Studio
Jan

vLLM

How to use Abbas8910/Shiksha-AI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abbas8910/Shiksha-AI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abbas8910/Shiksha-AI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abbas8910/Shiksha-AI

Ollama
How to use Abbas8910/Shiksha-AI with Ollama:
```
ollama run hf.co/Abbas8910/Shiksha-AI
```

Unsloth Studio

How to use Abbas8910/Shiksha-AI 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 Abbas8910/Shiksha-AI 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 Abbas8910/Shiksha-AI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abbas8910/Shiksha-AI to start chatting

How to use Abbas8910/Shiksha-AI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Abbas8910/Shiksha-AI

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": "Abbas8910/Shiksha-AI"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abbas8910/Shiksha-AI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Abbas8910/Shiksha-AI

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 Abbas8910/Shiksha-AI

Run Hermes

hermes

Docker Model Runner
How to use Abbas8910/Shiksha-AI with Docker Model Runner:
```
docker model run hf.co/Abbas8910/Shiksha-AI
```

Lemonade

How to use Abbas8910/Shiksha-AI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abbas8910/Shiksha-AI

Run and chat with the model

lemonade run user.Shiksha-AI-{{QUANT_TAG}}

List all available models

lemonade list

Shiksha AI – NCERT-tuned Qwen2.5-1.5B (GGUF)

Shiksha AI is a 1.5B-parameter Qwen2.5-based model fine-tuned on NCERT-aligned educational instructions to support homework help, concept explanations, quizzes, summarisation, and code generation for school students in India.
This repository provides a quantized GGUF variant optimized for fully on-device inference on mid-range Android phones via llama.cpp.

Intended use

NCERT-aligned question answering and explanations (middle and high school).
Homework help, chapter summaries, quiz-style questions.
Simple code generation examples for Python and related curriculum topics.
Offline deployment in mobile apps (e.g., our Shiksha AI Android app).

Out of scope / limitations

Not suitable for medical, legal, or financial advice.
Not designed for general open-domain chat beyond education.
Training data focuses on NCERT curricula; performance outside that domain is not guaranteed.

Model details

Base model: Qwen2.5-1.5B (Qwen/Qwen2.5-1.5B).
Parameters: ~1.5B (2B-class GGUF quantized).
Quantization: q4_k_m GGUF (986 MB).
Architecture: Qwen2-style decoder-only transformer.
Context length: 2,048 tokens (training setting in our paper).

For full training hyperparameters, see our article “” (Springer Nature, under review).

Training data

The model was fine-tuned on an instruction-tuning dataset derived from NCERT materials and synthetic educational prompts:

NCERT textbooks across multiple subjects (e.g., physics, chemistry, biology, mathematics, social science).
Task types include instruction-following, multi-step reasoning, explanation, summarisation, and code examples aligned with curriculum topics.
Dataset size: ~119,524 instruction–response pairs.

Once released, the dataset will be hosted at:

Dataset repo: https://huggingface.co/datasets/Abbas8910/Shiksha-AI-NCERT (JSONL or Parquet).

Please refer to the dataset card for details on preprocessing and licensing.

Training procedure

Method: Low-Rank Adaptation (LoRA / RS-LoRA) on top of the base Qwen2.5-1.5B weights.
Max sequence length: 2,048 tokens.
Optimizer: AdamW (8‑bit), weight decay 0.01, gradient clipping 1.0.
Learning rate: (2 \times 10^{-5}) with cosine decay and warmup.
Effective batch size: 32 sequences (per-device batch 16, grad accumulation 2).
Epochs: 1 pass over the NCERT dataset.
Trainable parameters: ~18.46M (LoRA parameters only).

More details, including loss curves and evaluation, are reported in our paper.

Evaluation

We report several automatic and benchmark metrics:

ROUGE‑1 / ROUGE‑L on held-out NCERT-style validation prompts.
MMLU high-school subjects: chemistry, physics, biology.
ARC‑Challenge subset for science reasoning.

In general, Shiksha AI outperforms comparable 1–2B open models in NCERT-style tasks while remaining under ~1.0 GB in GGUF format, making it suitable for offline mobile deployment.

How to use (llama.cpp example)

Download the GGUF file (e.g. via huggingface-cli or direct URL) and run:

# Example with llama.cpp
./main -m Shiksha_AI.gguf \
  -p "Explain the law of conservation of energy for a class 9 NCERT student." \
  -n 256

Make sure to adapt context length and sampling parameters to your device.

Citation

If you use Shiksha AI in your research, please cite:

@article{abbas2025shikshaai,
  title   = {Shiksha AI: An On-Device Small Language Model for Offline Educational Assistance in Resource-Constrained Environments},
  author  = {Abbas A. M. and Remya K. Sasi},
  journal = {<Journal name>},
  year    = {2025},
  note    = {Preprint / Under review}
}

License

This model is released under the Apache-2.0 license (see LICENSE file).
Please ensure your use complies with local regulations and with the licenses of the underlying NCERT materials and base model.

Downloads last month: 2

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Abbas8910/Shiksha-AI

Base model

Qwen/Qwen2.5-1.5B

Quantized

(68)

this model

Abbas8910
/

Shiksha-AI