Instructions to use prash616/Indica-1.7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prash616/Indica-1.7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prash616/Indica-1.7B-GGUF",
	filename="qwen3-1.7b.Q4_K_M.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 prash616/Indica-1.7B-GGUF 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 prash616/Indica-1.7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prash616/Indica-1.7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prash616/Indica-1.7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prash616/Indica-1.7B-GGUF: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 prash616/Indica-1.7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prash616/Indica-1.7B-GGUF: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 prash616/Indica-1.7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prash616/Indica-1.7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prash616/Indica-1.7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prash616/Indica-1.7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prash616/Indica-1.7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prash616/Indica-1.7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prash616/Indica-1.7B-GGUF:Q4_K_M

Ollama
How to use prash616/Indica-1.7B-GGUF with Ollama:
```
ollama run hf.co/prash616/Indica-1.7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use prash616/Indica-1.7B-GGUF 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 prash616/Indica-1.7B-GGUF 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 prash616/Indica-1.7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prash616/Indica-1.7B-GGUF to start chatting

How to use prash616/Indica-1.7B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prash616/Indica-1.7B-GGUF: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": "prash616/Indica-1.7B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prash616/Indica-1.7B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prash616/Indica-1.7B-GGUF: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 prash616/Indica-1.7B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use prash616/Indica-1.7B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prash616/Indica-1.7B-GGUF:Q4_K_M

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 "prash616/Indica-1.7B-GGUF:Q4_K_M" \
  --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 prash616/Indica-1.7B-GGUF with Docker Model Runner:
```
docker model run hf.co/prash616/Indica-1.7B-GGUF:Q4_K_M
```

Lemonade

How to use prash616/Indica-1.7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prash616/Indica-1.7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Indica-1.7B-GGUF-Q4_K_M

List all available models

lemonade list

prash616 commited on Feb 22

Commit

a66910a

verified ·

1 Parent(s): c506a26

Update README.md

Browse files

Files changed (1) hide show

README.md +53 -35

README.md CHANGED Viewed

@@ -1,4 +1,6 @@
 ---
 language:
 - hi
 - en
@@ -7,47 +9,63 @@ language:
 - te
 - mr
 - gu
 tags:
 - indian-languages
 - hinglish
 - reasoning
-- instruction-tuned
-- legal
-- agriculture
-base_model: unsloth/Qwen3-1.7B
-license: apache-2.0
 ---
-# Indica-1.7B — India Ka Apna AI 🇮🇳
-Indian multilingual AI assistant built by [Prashant](https://huggingface.co/prash616).
-## Training Pipeline
-```
-Qwen3-1.7B → Pretrain (Hindi Wikipedia)
-           → SFT (Indic instruct, Hinglish, Legal, Agriculture)
-           → GRPO (Hindi chain-of-thought reasoning)
-           → DPO (preference alignment)
-           → Indica-1.7B
-```
-## Capabilities
-- 🇮🇳 Hindi, Hinglish, English fluency
-- ⚖️ Indian Legal (IPC, RTI, consumer rights)
-- 🌾 Agriculture (MSP, PM-Kisan, crop advice)
-- 📚 Education (UPSC, JEE, NEET guidance)
-- 🧮 Reasoning with chain-of-thought
-## Quick Start
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("prash616/Indica-1.7B-Full")
-tokenizer = AutoTokenizer.from_pretrained("prash616/Indica-1.7B-Full")
-```
-## Ollama
 ```bash
 ollama run hf.co/prash616/Indica-1.7B-GGUF
-```
-Built with ❤️ for India by Prashant (prash616)

 ---
+license: apache-2.0
+base_model: unsloth/Qwen3-1.7B
 language:
 - hi
 - en
 - te
 - mr
 - gu
+- kn
+- ml
+- pa
+pipeline_tag: text-generation
 tags:
 - indian-languages
 - hinglish
 - reasoning
+- gguf
+- quantization
+- unsloth
 ---
+# Indica-1.7B-GGUF — Optimized for the Indian Context 🇮🇳
+Indica-1.7B is a lightweight, high-performance model specifically post-trained to serve the linguistic and cultural nuances of India. Built upon the **Qwen3-1.7B** architecture, this model has undergone a rigorous multi-stage alignment process to excel in Hindi, Hinglish, and various regional dialects while maintaining strong reasoning capabilities.
+This repository provides the model in **GGUF** format, optimized for local inference on consumer hardware using tools like **Ollama**, **llama.cpp**, and **LM Studio**.
+## 🚀 Model Highlights
+- **Specialized Post-Training:** Tailored for Indian Law (IPC/BNS), Agriculture (MSP/PM-Kisan), and National Examinations (UPSC/JEE).
+- **Multilingual Mastery:** Fluent in Hindi-English code-switching (Hinglish) and supports multiple regional Indian languages.
+- **Thinking Paradigm:** Utilizes a native "thinking mode" for complex reasoning tasks via Chain-of-Thought (CoT).
+- **Efficient Deployment:** The 1.7B parameter count ensures fast, private, and local execution with minimal RAM requirements.
+## 🛠 Training Pipeline
+The model was developed through a specialized four-stage alignment strategy:
+1. **Foundational Pre-training:** Fine-tuned on Hindi Wikipedia to establish deep linguistic roots.
+2. **Supervised Fine-Tuning (SFT):** Trained on high-quality instruction datasets covering Indian law, agriculture, and everyday Hinglish conversations.
+3. **GRPO (Reinforcement Learning):** Aligned using Group Relative Policy Optimization to reward logical reasoning and the use of `<think>` tags.
+4. **DPO (Preference Alignment):** Final behavioral polish using Direct Preference Optimization to ensure a helpful, polite, and culturally aware persona.
+## 📊 Key Datasets
+- **Indic-Instruct & Aya:** For foundational instruction-following in Indian languages.
+- **Hinglish-Everyday-Conversations:** To master natural code-switching used in urban India.
+- **Viber1 Indian Law Dataset:** Specialized knowledge of the Indian Penal Code and Constitution.
+- **GSM8K:** For mathematical and logical reasoning alignment.
+- **UltraFeedback Binarized:** For preference alignment and behavioral safety.
+## 📦 Quantization Details
+These GGUF files were created using `llama.cpp` through the Unsloth library.
+| File | Size | Optimization | Recommended Use |
+| :--- | :--- | :--- | :--- |
+| **Q4_K_M** | ~1.1 GB | Balanced | Best for general use on mobile or low-RAM devices. |
+| **Q8_0** | ~1.8 GB | High Precision | Recommended for technical tasks (Law/Math). |
+## 💻 How to Use
+### With Ollama
+You can run this model directly via the Hugging Face URL:
 ```bash
 ollama run hf.co/prash616/Indica-1.7B-GGUF
+ Limitations & Disclaimer
+While Indica-1.7B is highly optimized for the Indian context, it is a 1.7B parameter model. It may occasionally exhibit hallucinations or repetition loops in very long conversations. For technical or legal queries, it is recommended to verify the output against official documentation.
+Developed by: Prashant (prash616)