Instructions to use fwizzer1/Fwizzer-R1-3B-RU-v2 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-v2 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-v2
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-RU-v2

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-v2
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-RU-v2

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-v2
# Run inference directly in the terminal:
./llama-cli -hf fwizzer1/Fwizzer-R1-3B-RU-v2

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-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fwizzer1/Fwizzer-R1-3B-RU-v2

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU-v2

LM Studio
Jan

vLLM

How to use fwizzer1/Fwizzer-R1-3B-RU-v2 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-v2"
# 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-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU-v2

Ollama
How to use fwizzer1/Fwizzer-R1-3B-RU-v2 with Ollama:
```
ollama run hf.co/fwizzer1/Fwizzer-R1-3B-RU-v2
```
Unsloth Desktop

How to use fwizzer1/Fwizzer-R1-3B-RU-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fwizzer1/Fwizzer-R1-3B-RU-v2

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "fwizzer1/Fwizzer-R1-3B-RU-v2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use fwizzer1/Fwizzer-R1-3B-RU-v2 with Docker Model Runner:
```
docker model run hf.co/fwizzer1/Fwizzer-R1-3B-RU-v2
```

Lemonade

How to use fwizzer1/Fwizzer-R1-3B-RU-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fwizzer1/Fwizzer-R1-3B-RU-v2

Run and chat with the model

lemonade run user.Fwizzer-R1-3B-RU-v2-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use fwizzer1/Fwizzer-R1-3B-RU-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fwizzer1/Fwizzer-R1-3B-RU-v2

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 fwizzer1/Fwizzer-R1-3B-RU-v2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use fwizzer1/Fwizzer-R1-3B-RU-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fwizzer1/Fwizzer-R1-3B-RU-v2

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 "fwizzer1/Fwizzer-R1-3B-RU-v2" \
  --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"

fwizzer1 commited on Sep 5

Commit

78384cb

verified ·

1 Parent(s): e565fcd

Update official documentation card

Browse files

Files changed (1) hide show

README.md +56 -186

README.md CHANGED Viewed

@@ -1,210 +1,80 @@
 ---
-base_model: unsloth/Ministral-3-3B-Instruct-2512-bnb-4bit
-library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:unsloth/Ministral-3-3B-Instruct-2512-bnb-4bit
-- lora
-- sft
-- transformers
-- trl
-- unsloth
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]
-### Framework versions
-- PEFT 0.19.1

 ---
+language:
+- ru
+- en
+license: apache-2.0
 pipeline_tag: text-generation
 tags:
+- reasoning
+- deepseek-r1
+- ru-deepthink-mega
+- mistral
+- ministral
+- text-generation
+- gguf
+- godot
+- procedural-generation
 ---
+# 🧠 Fwizzer-R1-3B-RU-v2
+<div align="center">
+**Вторая улучшенная версия мыслящей языковой модели Fwizzer-R1**
+*The Second Generation of Fwizzer-R1 Reasoning LLM*
+[![Dataset](https://img.shields.io/badge/Dataset-ru--deepthink--mega-blue)](https://huggingface.co/datasets/fwizzer1/ru-deepthink-mega)
+[![License](https://img.shields.io/badge/License-Apache%202.0-green)](LICENSE)
+</div>
+---
+## 🇷🇺 Описание на русском
+**Fwizzer-R1-3B-RU-v2** — это компактная, но глубоко мыслящая языковая модель, дообученная на флагманском мега-датасете [**`fwizzer1/ru-deepthink-mega`**](https://huggingface.co/datasets/fwizzer1/ru-deepthink-mega) (17 281 пример со 100% размышлениями).
+### 🚀 Ключевые преимущества версии v2:
+1. **100% Reasoning:** Модель ВСЕГДА сначала размышляет внутри блока `<think> ... </think>` перед формированием ответа.
+2. **Думание в стоке (Stock Thinking):** В GGUF зашит шаблон `chat_template.jinja`, открывающий тег `<think>` автоматически даже без системного промпта.
+3. **Процедурная генерация & Godot 4 GDScript:** Глубокие знания игровых алгоритмов (клеточные автоматы для пещер, BSP комнаты/подземелья, шум Перлина, лабиринты, генерация лута и аффиксов).
+4. **Защита от логических капканов:** Уверенно решает ловушки токенизации (9.11 vs 9.9, подсчёт букв в словах, парадокс Монти Холла, управление ресурсами).
+5. **Самопроверка (Self-Correction):** Умеет перепроверять свои шаги, пересчитывать формулы и исправлять собственные ошибки на лету.
+---
+## 🇬🇧 English Description
+**Fwizzer-R1-3B-RU-v2** is an advanced, lightweight reasoning language model fine-tuned on the comprehensive [**`fwizzer1/ru-deepthink-mega`**](https://huggingface.co/datasets/fwizzer1/ru-deepthink-mega) dataset (17 281 verified Chain-of-Thought samples).
+### 🚀 Key Improvements in v2:
+1. **100% Reasoning by Default:** The model methodically analyzes problems inside `<think> ... </think>` tags before delivering the final answer.
+2. **Built-in Stock Thinking:** Native `chat_template.jinja` automatically activates `<think>` tags without requiring custom system prompts.
+3. **Procedural Generation & Game Development:** Specialized knowledge in **Godot 4 GDScript** and **Python** (Cellular Automata caves, BSP dungeon generators, Perlin noise biomes, A* pathfinding, dynamic item affix generation).
+4. **Tokenizer & Logic Trap Immunity:** Handles subtle math/logic pitfalls (e.g. 9.11 vs 9.9, letter counting in words, Monty Hall problem).
+5. **Self-Correction & Reflection:** Capable of reconsidering intermediate reasoning steps and verifying mathematical correctness on the fly.
+---
+## 📦 Доступные квантизации GGUF / Available GGUF Models:
+| Файл | Квантование | Размер | Описание / Description |
+| :--- | :---: | :---: | :--- |
+| **`Fwizzer-R1-3B-v2Speed.gguf`** | Q4_K_M | ~2.0 GB | Лёгкая и быстрая, запуск на любых ПК и смартфонах / Ultra-fast inference |
+| **`Fwizzer-R1-3B-v2Balanced.gguf`** | Q5_K_M | ~2.4 GB | Золотая середина между скоростью и интеллектом / Recommended balance |
+| **`Fwizzer-R1-3B-v2Max.gguf`** | Q8_0 | ~3.4 GB | Максимальный интеллект, точность без потерь / Maximum reasoning quality |
+---
+## 🛠️ Запуск в LM Studio / Ollama:
+1. Скачайте нужную квантизацию GGUF (например, `Fwizzer-R1-3B-v2Balanced.gguf`).
+2. Пресет `Fwizzer-R1.preset.json` уже находится в репозитории — LM Studio автоматически свернёт рассуждения в красивый блок **Thought**.
+3. **Шаблон вывода:**
+```
+<think>
+[Пошаговый ход мысли модели...]
+</think>
+[Финальный структурированный ответ]
+```