Instructions to use Erebus007/NCERT_3B_v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Erebus007/NCERT_3B_v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Erebus007/NCERT_3B_v0.1",
	filename="NCERT_3B_v0.1.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Erebus007/NCERT_3B_v0.1 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Erebus007/NCERT_3B_v0.1
# Run inference directly in the terminal:
llama cli -hf Erebus007/NCERT_3B_v0.1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Erebus007/NCERT_3B_v0.1
# Run inference directly in the terminal:
llama cli -hf Erebus007/NCERT_3B_v0.1

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 Erebus007/NCERT_3B_v0.1
# Run inference directly in the terminal:
./llama-cli -hf Erebus007/NCERT_3B_v0.1

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 Erebus007/NCERT_3B_v0.1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Erebus007/NCERT_3B_v0.1

Use Docker

docker model run hf.co/Erebus007/NCERT_3B_v0.1

LM Studio
Jan

vLLM

How to use Erebus007/NCERT_3B_v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Erebus007/NCERT_3B_v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Erebus007/NCERT_3B_v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Erebus007/NCERT_3B_v0.1

Ollama
How to use Erebus007/NCERT_3B_v0.1 with Ollama:
```
ollama run hf.co/Erebus007/NCERT_3B_v0.1
```

Unsloth Studio

How to use Erebus007/NCERT_3B_v0.1 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 Erebus007/NCERT_3B_v0.1 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 Erebus007/NCERT_3B_v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Erebus007/NCERT_3B_v0.1 to start chatting

How to use Erebus007/NCERT_3B_v0.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Erebus007/NCERT_3B_v0.1

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": "Erebus007/NCERT_3B_v0.1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Erebus007/NCERT_3B_v0.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Erebus007/NCERT_3B_v0.1

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 Erebus007/NCERT_3B_v0.1

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Erebus007/NCERT_3B_v0.1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Erebus007/NCERT_3B_v0.1

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Erebus007/NCERT_3B_v0.1" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Erebus007/NCERT_3B_v0.1 with Docker Model Runner:
```
docker model run hf.co/Erebus007/NCERT_3B_v0.1
```

Lemonade

How to use Erebus007/NCERT_3B_v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Erebus007/NCERT_3B_v0.1

Run and chat with the model

lemonade run user.NCERT_3B_v0.1-{{QUANT_TAG}}

List all available models

lemonade list

NCERT 3B v0.1 (GGUF)

Model Description

NCERT 3B v0.1 is a 3B-parameter language model fine-tuned specifically on NCERT educational datasets. Rather than being trained from scratch as a base model, it has been deliberately fine-tuned to assist students and educators by providing accurate, curriculum-aligned explanations, summaries, and Q&A capabilities.

This repository contains the GGUF formatted model, which is highly optimized for local inference on consumer hardware.

Intended Uses & Limitations

Intended Uses

Educational Assistance & Tutoring: Designed to act as an interactive assistant for navigating the NCERT curriculum. It can summarize chapters, explain concepts in simpler terms, and answer textbook-aligned questions.
Content & Quiz Generation: Well-suited for generating practice questions, filling in blanks, creating multiple-choice questions (MCQs), and developing study guides strictly mapped to the text.
Curriculum-Specific Tasks: Optimized for processing text structures specific to secondary school subjects, making it highly effective for localized educational extraction.

Limitations

Scope & Domain Constraints: The model is highly specialized for the NCERT curriculum. Its performance or factual accuracy on non-educational topics, advanced professional domains, or alternative international syllabi may be significantly limited.
Parameter Size Limitations: As a 3B parameter model, it is highly efficient for targeted text generation but may struggle with deep, multi-step logical reasoning or abstract mathematical proofs compared to massive frontier models.
Potential for Hallucination: Like all language models, it can occasionally generate plausible-sounding but incorrect details. Outputs should always be cross-referenced with official textbooks for critical academic preparation.
Syllabus Versioning: The model’s knowledge base is anchored to specific editions of the NCERT textbooks. Any recent rationalizations or chapter updates made by the board may not be accurately reflected.

Training Data

The model was fine-tuned on a custom, locally tagged dataset extracted directly from NCERT curriculum materials. This includes fully converted and structured subject data, such as the Class 9 English curriculum, to ensure high-fidelity responses to textbook queries.

How to Get Started with the Model

Since this model is in the GGUF format, you can easily run it locally using tools like LM Studio, GPT4All, or llama.cpp.

Downloads last month: 273

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants