Text Generation
Safetensors
GGUF
Russian
English
mistral3
reasoning
deepseek-r1
ru-deepthink-11k
mistral
conversational
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
- llama.cpp
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
Update README with full documentation and reasoning tags
Browse files
README.md
CHANGED
|
@@ -3,110 +3,49 @@ language:
|
|
| 3 |
- ru
|
| 4 |
- en
|
| 5 |
license: apache-2.0
|
|
|
|
| 6 |
tags:
|
| 7 |
- reasoning
|
| 8 |
- deepseek-r1
|
| 9 |
- think
|
| 10 |
-
-
|
|
|
|
| 11 |
- gguf
|
| 12 |
-
-
|
| 13 |
- unsloth
|
| 14 |
-
- code
|
| 15 |
-
- programming
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
-
base_model: mistralai/Ministral-3-3B-Instruct-2512
|
| 18 |
---
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
**A lightweight, high-performance Russian reasoning model powered by Ministral 3B with DeepSeek-R1 style step-by-step thinking.**
|
| 25 |
-
|
| 26 |
-
[](https://huggingface.co/datasets/fwizzer1/ru-deepthink-11k)
|
| 27 |
-
[](https://opensource.org/licenses/Apache-2.0)
|
| 28 |
-
[](#-available-gguf-quantizations)
|
| 29 |
-
|
| 30 |
-
</div>
|
| 31 |
-
|
| 32 |
-
---
|
| 33 |
-
|
| 34 |
-
## 🌟 Overview
|
| 35 |
-
|
| 36 |
-
**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).
|
| 37 |
-
|
| 38 |
-
It integrates native `<think>...</think>` internal monologue before every response, making it exceptional at:
|
| 39 |
-
- **💻 Code Generation & Engineering**: Clean multi-language programming, algorithm design, debugging, refactoring, and software architecture.
|
| 40 |
-
- **🧩 Math & Logic Reasoning**: Step-by-step problem solving, formal logic, and self-verification.
|
| 41 |
-
- **⚡️ 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).
|
| 42 |
-
|
| 43 |
-
---
|
| 44 |
-
|
| 45 |
-
## 📦 Available GGUF Quantizations
|
| 46 |
-
|
| 47 |
-
| File | Size | VRAM Required | Recommended For |
|
| 48 |
-
| :--- | :--- | :--- | :--- |
|
| 49 |
-
| **`Ministral-3-3B-Instruct-2512.Q4_K_M.gguf`** | **2.05 GB** | **~2.8 GB (with 4096 ctx)** | **Recommended (Best speed/accuracy balance)** |
|
| 50 |
-
| **`Ministral-3-3B-Instruct-2512.Q8_0.gguf`** | **3.41 GB** | **~4.2 GB (with 4096 ctx)** | **Maximum precision** |
|
| 51 |
-
|
| 52 |
-
---
|
| 53 |
-
|
| 54 |
-
## 🚀 Quickstart in LM Studio
|
| 55 |
-
|
| 56 |
-
1. Open **LM Studio** and go to the **🔍 Search** tab.
|
| 57 |
-
2. Search for:
|
| 58 |
-
```text
|
| 59 |
-
fwizzer1/Fwizzer-R1-3B-RU
|
| 60 |
-
```
|
| 61 |
-
3. Click **Download** on `Q4_K_M`.
|
| 62 |
-
4. Load the model and start chatting! The model will automatically output reasoning thoughts in `<think>...</think>` blocks.
|
| 63 |
|
| 64 |
---
|
| 65 |
|
| 66 |
-
##
|
| 67 |
-
|
| 68 |
-
```python
|
| 69 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 70 |
-
import torch
|
| 71 |
|
| 72 |
-
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
model_id,
|
| 77 |
-
torch_dtype=torch.bfloat16,
|
| 78 |
-
device_map="auto"
|
| 79 |
-
)
|
| 80 |
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
{"role": "user", "content": prompt}
|
| 84 |
-
]
|
| 85 |
-
|
| 86 |
-
inputs = tokenizer.apply_chat_template(
|
| 87 |
-
messages,
|
| 88 |
-
add_generation_prompt=True,
|
| 89 |
-
return_tensors="pt"
|
| 90 |
-
).to("cuda")
|
| 91 |
-
|
| 92 |
-
outputs = model.generate(
|
| 93 |
-
inputs,
|
| 94 |
-
max_new_tokens=2048,
|
| 95 |
-
temperature=0.6,
|
| 96 |
-
top_p=0.95
|
| 97 |
-
)
|
| 98 |
-
|
| 99 |
-
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
|
| 100 |
-
```
|
| 101 |
-
|
| 102 |
-
---
|
| 103 |
|
| 104 |
-
|
|
|
|
| 105 |
|
| 106 |
-
|
|
|
|
| 107 |
|
| 108 |
---
|
| 109 |
|
| 110 |
-
##
|
| 111 |
|
| 112 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- ru
|
| 4 |
- en
|
| 5 |
license: apache-2.0
|
| 6 |
+
base_model: mistralai/Ministral-3B-Instruct-2410
|
| 7 |
tags:
|
| 8 |
- reasoning
|
| 9 |
- deepseek-r1
|
| 10 |
- think
|
| 11 |
+
- ru-deepthink-11k
|
| 12 |
+
- text-generation
|
| 13 |
- gguf
|
| 14 |
+
- llama.cpp
|
| 15 |
- unsloth
|
|
|
|
|
|
|
| 16 |
pipeline_tag: text-generation
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# 🧠 Fwizzer-R1-3B-RU (Thinking Reasoning LLM)
|
| 20 |
|
| 21 |
+
**Fwizzer-R1-3B-RU** — это мощная русскоязычная мыслящая языковая модель (Reasoning LLM) на архитектуре Ministral 3B, обученная по методологии **DeepSeek-R1** на датасете [fwizzer1/ru-deepthink-11k](https://huggingface.co/datasets/fwizzer1/ru-deepthink-11k) (11 000 пошаговых диалогов).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
---
|
| 24 |
|
| 25 |
+
## 🌟 Ключевые возможности
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
+
1. 🏷 **Вшитая идентичность и системный промпт (general.name)**
|
| 28 |
+
* Модель на уровне ядра знает своё имя: **Fwizzer-R1-3B-RU**.
|
| 29 |
+
* Вшит дефолтный системный промпт:
|
| 30 |
+
> *«Ты думающая нейросеть а зовут тебя Fwizzer-R1-3B-RU. Весь ход мыслей и шаги пиши внутри тегов <think>(напиши сначала) и </think>(напиши по окончанию рассуждений), а итоговый ответ — обязательно после них.»*
|
| 31 |
|
| 32 |
+
2. 🧠 **Глубокое мышление (DeepSeek-R1 Architecture)**
|
| 33 |
+
* Перед ответом модель активирует внутренний «черновик» в тегах `<think> ... </think>`, анализирует скрытые подвохи, краевые случаи и выводит математические доказательства.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
3. 🎭 **Графическая шторка размышлений в LM Studio (Reasoning UI)**
|
| 36 |
+
* В репозиторий вшит файл `model.yaml` с флагами `reasoning: true` и `reasoningFormat: deepseek`. При скачива��ии в LM Studio мысли автоматически сворачиваются в красивую плашку *Thought for X.Xs*.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
+
4. 🛡 **Защита от сбоев (Fix Error 500)**
|
| 39 |
+
* Оптимизированный Jinja-шаблон чата без конфликтов системных сообщений, полная поддержка Flash Attention 2.
|
| 40 |
|
| 41 |
+
5. 📚 **Расширенный контекст (до 256K токенов с RoPE YaRN Scaling)**
|
| 42 |
+
* Поддержка длинных кодовых баз, документаций и книг.
|
| 43 |
|
| 44 |
---
|
| 45 |
|
| 46 |
+
## 🚀 Запуск в LM Studio
|
| 47 |
|
| 48 |
+
1. Откройте **LM Studio**.
|
| 49 |
+
2. В строке поиска введите: `fwizzer1/Fwizzer-R1-3B-RU`.
|
| 50 |
+
3. Скачайте квантование **`Fwizzer-R1-3B.Q4_K_M.gguf`** (2.1 ГБ) или **`Q8_0`** (3.4 ГБ).
|
| 51 |
+
4. Запустите чат — модель сразу готова к работе с автоматическим блоком размышлений!
|