Instructions to use Digirocket/drok-v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Digirocket/drok-v5 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 Digirocket/drok-v5:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Digirocket/drok-v5:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Digirocket/drok-v5:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Digirocket/drok-v5: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 Digirocket/drok-v5:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Digirocket/drok-v5: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 Digirocket/drok-v5:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Digirocket/drok-v5:Q4_K_M

Use Docker

docker model run hf.co/Digirocket/drok-v5:Q4_K_M

LM Studio
Jan

vLLM

How to use Digirocket/drok-v5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Digirocket/drok-v5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Digirocket/drok-v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Digirocket/drok-v5:Q4_K_M

Ollama
How to use Digirocket/drok-v5 with Ollama:
```
ollama run hf.co/Digirocket/drok-v5:Q4_K_M
```

Unsloth Studio

How to use Digirocket/drok-v5 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 Digirocket/drok-v5 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 Digirocket/drok-v5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Digirocket/drok-v5 to start chatting

How to use Digirocket/drok-v5 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Digirocket/drok-v5: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": "Digirocket/drok-v5:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Digirocket/drok-v5 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Digirocket/drok-v5: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 Digirocket/drok-v5:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Digirocket/drok-v5 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Digirocket/drok-v5: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 "Digirocket/drok-v5: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 Digirocket/drok-v5 with Docker Model Runner:
```
docker model run hf.co/Digirocket/drok-v5:Q4_K_M
```

Lemonade

How to use Digirocket/drok-v5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Digirocket/drok-v5:Q4_K_M

Run and chat with the model

lemonade run user.drok-v5-Q4_K_M

List all available models

lemonade list

drok-v5 / README.md

DigirocketTeam

Upload README.md with huggingface_hub

145e72d verified 2 months ago

preview code

Raw

History Blame Contribute Delete

2.29 kB

	---
	license: apache-2.0
	language:
	- en
	- hi
	pipeline_tag: text-generation
	tags:
	- digirocket
	- digital-marketing
	- chat
	- gguf
	- conversational
	- qwen2.5
	base_model: Qwen/Qwen2.5-7B-Instruct
	---

	# DROK v5 — DigiRocket Technologies AI Assistant

	Fine-tuned Qwen2.5-7B-Instruct specialized for DigiRocket Technologies — a
	digital marketing and web development agency.

	## What's new in v5

	- Conversational quality boost: ~400 conversational pairs added (greetings,
	user self-introductions, memory-question handling, small talk, identity
	Q&A) for natural, warm responses on common chitchat patterns.
	- System prompt: refined CONVERSATIONAL PATTERNS section ensures refusal
	templates only fire for unverifiable factual claims, never for the user's
	own identity or casual interaction.
	- Retrieval-augmented: paired with an expanded Pinecone RAG index that
	adds ~1,300 general digital-marketing knowledge chunks (sourced from
	Wikipedia under CC-BY-SA + curated FAQs). The model itself stays focused
	on DigiRocket; broad marketing knowledge is retrieved at query time.

	## Specialization

	DROK is an expert in:
	- DigiRocket Services (pricing tiers, team, offices, case studies)
	- Digital Marketing (SEO, SEM, SMM, CRO, email marketing, content)
	- Web Development (responsive design, e-commerce platforms, UI/UX)
	- Branding (logo design, visual identity, brand storytelling)

	## Training Details

	- Base model: [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
	- Method: QLoRA 4-bit fine-tuning (NF4 quantization, LoRA r=16)
	- Dataset: 884 pairs (504 DigiRocket-specific + 380 conversational,
	template-generated — NO LLM-synthesised pairs to avoid hallucination)
	- Epochs: 5–7
	- Training infrastructure: Lightning.ai Tesla T4 (16 GB)

	## Quantization

	This release is the Q4_K_M GGUF quantized version (~4.5 GB),
	optimised for llama.cpp / HF Inference Endpoints serving on a T4 GPU.

	## Languages

	English and Hinglish (English-Hindi code-switch), reflecting DigiRocket's
	primary client base.

	## Company

	DigiRocket Technologies — global digital marketing agency:
	- IN: Gurgaon, India (HQ)
	- US: Dover, USA
	- UK: London, UK

	Websites: [digirocket.io](https://www.digirocket.io)