Instructions to use Bhishaj/Vidhik-Llama-1B-GGU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Bhishaj/Vidhik-Llama-1B-GGU 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 Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Bhishaj/Vidhik-Llama-1B-GGU: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 Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Bhishaj/Vidhik-Llama-1B-GGU: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 Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M

Use Docker

docker model run hf.co/Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M

LM Studio
Jan

vLLM

How to use Bhishaj/Vidhik-Llama-1B-GGU with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M

Ollama
How to use Bhishaj/Vidhik-Llama-1B-GGU with Ollama:
```
ollama run hf.co/Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M
```

Unsloth Studio

How to use Bhishaj/Vidhik-Llama-1B-GGU 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 Bhishaj/Vidhik-Llama-1B-GGU 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 Bhishaj/Vidhik-Llama-1B-GGU to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Bhishaj/Vidhik-Llama-1B-GGU to start chatting

How to use Bhishaj/Vidhik-Llama-1B-GGU with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Bhishaj/Vidhik-Llama-1B-GGU: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": "Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Bhishaj/Vidhik-Llama-1B-GGU with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Bhishaj/Vidhik-Llama-1B-GGU: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 Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Bhishaj/Vidhik-Llama-1B-GGU with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Bhishaj/Vidhik-Llama-1B-GGU: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 "Bhishaj/Vidhik-Llama-1B-GGU: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 Bhishaj/Vidhik-Llama-1B-GGU with Docker Model Runner:
```
docker model run hf.co/Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M
```

Lemonade

How to use Bhishaj/Vidhik-Llama-1B-GGU with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Bhishaj/Vidhik-Llama-1B-GGU:Q4_K_M

Run and chat with the model

lemonade run user.Vidhik-Llama-1B-GGU-Q4_K_M

List all available models

lemonade list

⚖️ Vidhik AI: Sovereign Legal SLM (1B)

📌 Model Summary

Vidhik AI is a highly optimized, domain-specific Small Language Model (SLM) engineered for the Indian Judiciary and MSME sector. Fine-tuned on a 1B parameter base, it specializes in drafting formal legal notices (e.g., MSMED Act delayed payments), analyzing case law, and navigating complex Indian officialese ("Babu-speak").

Built with a focus on Edge Compute, this model is designed to run locally on highly constrained hardware (like a 4GB GTX 1050) while retaining the ability to process massive context windows using Google TurboQuant.

Developer: Gaurav / Bhishaj Technologies
Base Model: Llama-3.2-1B-Instruct
Language(s): English, Hindi (Indic Legal Terminology)
License: Llama 3.2 Community License

🛠️ Training & MLOps Architecture

To bypass local hardware constraints (4GB VRAM), the model was trained using a hybrid cloud-edge pipeline:

1. Data Engineering

Corpus: Curated and filtered Indian Legal QA datasets (Techmaestro369/indian-legal-texts-finetuning) and multilingual judiciary data (coild-aikosh/Judiciary_v2).
Formatting: Converted raw unstructured legal texts into strict Alpaca/ShareGPT instruction formats for deterministic instruction following.

2. Fine-Tuning Setup

Compute: Kaggle Dual T4 GPUs (32GB VRAM combined).
Optimization: Utilized Unsloth for a 70% VRAM reduction during fine-tuning, accelerating the training process by 2x.
Methodology: Parameter-Efficient Fine-Tuning (PEFT) using QLoRA.

3. Guardrails & Alignment

Trained with strict negative stop-sequences and deterministic decoding parameters (Temperature = 0.0) to cure the base model of MCQ-loop hallucinations.
Aligned to a "Senior Advocate, Supreme Court of India" persona for formal, zero-fluff document generation.

⚡ Edge Deployment & Google TurboQuant (2026)

This model is specifically compiled to run on legacy/constrained hardware.

By utilizing Google TurboQuant, the model compresses the KV-cache to 3-bits during runtime. This allows for 128k context windows (essential for processing long Indian government gazettes and supreme court rulings) without triggering OOM (Out of Memory) crashes on a 4GB GPU, maintaining a throughput of ~24.5 tokens/sec.

💻 Usage: Running Locally (TurboQuant Enabled)

To achieve 6x KV-cache compression on your local machine:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from turboquant import TurboQuantCache

repo_id = "Bhishaj/Vidhik-Llama-1B-GGU" 
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="cuda")

# Initialize TurboQuant 4-bit Cache for 4GB VRAM support
tq_cache = TurboQuantCache(bits=4, compute_device="cuda")

prompt = "TASK: Draft a formal legal notice for my client 'M/s Vidhik Electronics' under MSMED Act Sections 15 & 16."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Generate with Compressed Context
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        past_key_values=tq_cache, # Injecting the TurboQuant cache
        max_new_tokens=512,
        temperature=0.0
    )

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 11

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for Bhishaj/Vidhik-Llama-1B-GGU

Base model

meta-llama/Llama-3.2-1B-Instruct

Quantized

(410)

this model

Bhishaj
/

Vidhik-Llama-1B-GGU

⚖️ Vidhik AI: Sovereign Legal SLM (1B)

📌 Model Summary

🛠️ Training & MLOps Architecture

1. Data Engineering

2. Fine-Tuning Setup

3. Guardrails & Alignment

⚡ Edge Deployment & Google TurboQuant (2026)

💻 Usage: Running Locally (TurboQuant Enabled)

Model tree for Bhishaj/Vidhik-Llama-1B-GGU

Datasets used to train Bhishaj/Vidhik-Llama-1B-GGU

Space using Bhishaj/Vidhik-Llama-1B-GGU 1