Instructions to use fwizzer1/Fwizzer-R1-3B-RU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use fwizzer1/Fwizzer-R1-3B-RU 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 fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-RU

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-RU

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 fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
./llama-cli -hf fwizzer1/Fwizzer-R1-3B-RU

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 fwizzer1/Fwizzer-R1-3B-RU
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fwizzer1/Fwizzer-R1-3B-RU

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU

LM Studio
Jan

vLLM

How to use fwizzer1/Fwizzer-R1-3B-RU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fwizzer1/Fwizzer-R1-3B-RU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fwizzer1/Fwizzer-R1-3B-RU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU

Ollama
How to use fwizzer1/Fwizzer-R1-3B-RU with Ollama:
```
ollama run hf.co/fwizzer1/Fwizzer-R1-3B-RU
```
Unsloth Desktop
Docker Model Runner
How to use fwizzer1/Fwizzer-R1-3B-RU with Docker Model Runner:
```
docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU
```

Lemonade

How to use fwizzer1/Fwizzer-R1-3B-RU with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fwizzer1/Fwizzer-R1-3B-RU

Run and chat with the model

lemonade run user.Fwizzer-R1-3B-RU-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

fwizzer1 commited on Aug 31

Commit

2e6a320

verified ·

1 Parent(s): 04c73de

Update README: generalized code generation description

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ tags:
 - lmstudio
 - unsloth
 - code
-- java
 pipeline_tag: text-generation
 base_model: mistralai/Ministral-3-3B-Instruct-2512
 ---
@@ -36,8 +36,8 @@ base_model: mistralai/Ministral-3-3B-Instruct-2512
 **Fwizzer-R1-3B-RU** is a specialized Russian reasoning language model fine-tuned on **11,000 verified multi-step reasoning dialogues** from [`fwizzer1/ru-deepthink-11k`](https://huggingface.co/datasets/fwizzer1/ru-deepthink-11k).
 It integrates native `<think>...</think>` internal monologue before every response, making it exceptional at:
-- **💻 Java & Minecraft Modding**: Deep knowledge of Forge, Fabric, Mixins, Spine 2D/3D math, concurrency, and performance optimization.
-- **🧩 Math & Logic Reasoning**: Step-by-step theorem proving, edge case analysis, and self-verification.
 - **⚡️ Ultra-fast Local Inference**: Optimized to run at **80+ tokens/sec** on budget GPUs (e.g. NVIDIA RTX 3050 4GB VRAM) with minimal memory footprint (~2.1 GB VRAM).
 ---
@@ -78,7 +78,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
-prompt = "Напиши на Java потокобезопасный Singleton с ленивой инициализацией."
 messages = [
     {"role": "user", "content": prompt}
 ]

 - lmstudio
 - unsloth
 - code
+- programming
 pipeline_tag: text-generation
 base_model: mistralai/Ministral-3-3B-Instruct-2512
 ---
 **Fwizzer-R1-3B-RU** is a specialized Russian reasoning language model fine-tuned on **11,000 verified multi-step reasoning dialogues** from [`fwizzer1/ru-deepthink-11k`](https://huggingface.co/datasets/fwizzer1/ru-deepthink-11k).
 It integrates native `<think>...</think>` internal monologue before every response, making it exceptional at:
+- **💻 Code Generation & Engineering**: Clean multi-language programming, algorithm design, debugging, refactoring, and software architecture.
+- **🧩 Math & Logic Reasoning**: Step-by-step problem solving, formal logic, and self-verification.
 - **⚡️ Ultra-fast Local Inference**: Optimized to run at **80+ tokens/sec** on budget GPUs (e.g. NVIDIA RTX 3050 4GB VRAM) with minimal memory footprint (~2.1 GB VRAM).
 ---
     device_map="auto"
 )
+prompt = "Реши задачу: найди сложность алгоритма быстрой сортировки в худшем случае и напиши реализацию."
 messages = [
     {"role": "user", "content": prompt}
 ]