Instructions to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B 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 FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B: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 FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B: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 FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M

Use Docker

docker model run hf.co/FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M

LM Studio
Jan
Ollama
How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with Ollama:
```
ollama run hf.co/FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M
```
Unsloth Desktop

How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M

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": "FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with Docker Model Runner:
```
docker model run hf.co/FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M
```

Lemonade

How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M

Run and chat with the model

lemonade run user.Crazy_Reasoning_Qwen2.5_3B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B: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 FGOTYT/Crazy_Reasoning_Qwen2.5_3B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FGOTYT/Crazy_Reasoning_Qwen2.5_3B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FGOTYT/Crazy_Reasoning_Qwen2.5_3B: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 "FGOTYT/Crazy_Reasoning_Qwen2.5_3B: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"

Crazy Reasoning Qwen2.5 3B 🧠

A funnny reasoning model, trained on a manual high-quality dataset! Don't use it in real problems.

He has "Secret Thoughts", after which he gives out an "Answer".

Officially supports English, Russian, Chinese, French, and Spanish (it has been in training dataset), but you can try other!

Context Length: 32,768.
Dataset: Custom without syntetic.
Prompt Example: "Hello!".
System Prompt: Set your language or other instructions for better perfomance, you can!

This model is best used for entertainment purposes (it will be funny if it actually works better in other things too). Author - FGOTYT (me).

Downloads last month: 30

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for FGOTYT/Crazy_Reasoning_Qwen2.5_3B

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(287)

this model

Collection including FGOTYT/Crazy_Reasoning_Qwen2.5_3B

Crazy_Reasoning 🧠

Collection

Multilingual reasoning model on Qwen2.5 1.5B, 3B, 7B base. • 4 items • Updated Dec 5, 2024 • 1