Instructions to use vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-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 vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF
# Run inference directly in the terminal:
llama cli -hf vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF
# Run inference directly in the terminal:
llama cli -hf vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF

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 vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF
# Run inference directly in the terminal:
./llama-cli -hf vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF

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 vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF

Use Docker

docker model run hf.co/vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF

LM Studio
Jan
Ollama
How to use vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF with Ollama:
```
ollama run hf.co/vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF
```

Unsloth Studio

How to use vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-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 vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-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 vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF with Docker Model Runner:
```
docker model run hf.co/vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF
```

Lemonade

How to use vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vivek-dodia/Deepseek-R1-8B-MikroTik-Distilled-GGUF

Run and chat with the model

lemonade run user.Deepseek-R1-8B-MikroTik-Distilled-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

MikroTik RouterOS Expert Assistant - DeepSeek-R1-Distill-Llama-8B LoRA (GGUF)

Model Description

This repository contains a fine-tuned version of the unsloth/DeepSeek-R1-Distill-Llama-8B large language model, specialized to act as an expert assistant for MikroTik RouterOS.

Fine-tuned for: Expert-level knowledge and assistance with MikroTik RouterOS networking, including configuration, troubleshooting, and understanding advanced features.

Intended Use: This model is designed for:

Answering technical questions about MikroTik RouterOS.
Providing step-by-step configuration guidance for MikroTik devices.
Assisting network engineers with troubleshooting MikroTik network issues.
Serving as a technical resource for users seeking expert-level MikroTik RouterOS information.

Model Architecture: LoRA (Low-Rank Adaptation) fine-tuned DeepSeek-R1-Distill-Llama-8B (8B parameters, Llama architecture). Converted to GGUF format for efficient inference with tools like llama.cpp.

Quantization: GGUF format, [Specify Quantization Type Here, e.g., q4_km] quantization.

Usage

The model is provided in GGUF format for efficient inference using llama.cpp and compatible tools.

Download GGUF Model:

Download the mikrotik-expert-model.gguf file from this repository.

Inference with llama.cpp/main (Example):

./main -m mikrotik-expert-model.gguf -p "Below is an instruction that describes a complex and critical task... ### Question: How do I configure a basic DHCP server on MikroTik? ### Response:" -n 500

Datasets Used for Fine-tuning:

The model was fine-tuned using a combination of these datasets:

vivek-dodia/synthetic-data-gemini-2.0-ComplexTroubleshooting
vivek-dodia/synthetic-data-gemini-2.0-ComplexConfigurations
vivek-dodia/mikrotik-openAPI
vivek-dodia/mikrotik-threads
vivek-dodia/synthetic-data-deepseekR1-ComplexTroubleshooting
vivek-dodia/mikrotik-github-repos
vivek-dodia/mikrotik-gitlab-repos
vivek-dodia/mikrotik-docs
ramixpe/bgp_questions_v3

Acknowledgements:

Fine-tuned using the Unsloth library.
Based on the DeepSeek-R1-Distill-Llama-8B base model by Unsloth AI and DeepSeek AI.
Built using the Transformers, Datasets, and TRL libraries from Hugging Face.

Contact

vivek.dodia@icloud.com

Downloads last month: 247

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support