Instructions to use gr0010/CustomThinker-0-8B 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 gr0010/CustomThinker-0-8B 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 gr0010/CustomThinker-0-8B:Q4_K_M # Run inference directly in the terminal: llama cli -hf gr0010/CustomThinker-0-8B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf gr0010/CustomThinker-0-8B:Q4_K_M # Run inference directly in the terminal: llama cli -hf gr0010/CustomThinker-0-8B: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 gr0010/CustomThinker-0-8B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf gr0010/CustomThinker-0-8B: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 gr0010/CustomThinker-0-8B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf gr0010/CustomThinker-0-8B:Q4_K_M
Use Docker
docker model run hf.co/gr0010/CustomThinker-0-8B:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use gr0010/CustomThinker-0-8B with Ollama:
ollama run hf.co/gr0010/CustomThinker-0-8B:Q4_K_M
- Unsloth Studio
How to use gr0010/CustomThinker-0-8B 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 gr0010/CustomThinker-0-8B 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 gr0010/CustomThinker-0-8B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for gr0010/CustomThinker-0-8B to start chatting
- Pi
How to use gr0010/CustomThinker-0-8B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf gr0010/CustomThinker-0-8B:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "gr0010/CustomThinker-0-8B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use gr0010/CustomThinker-0-8B with Docker Model Runner:
docker model run hf.co/gr0010/CustomThinker-0-8B:Q4_K_M
- Lemonade
How to use gr0010/CustomThinker-0-8B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull gr0010/CustomThinker-0-8B:Q4_K_M
Run and chat with the model
lemonade run user.CustomThinker-0-8B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use gr0010/CustomThinker-0-8B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf gr0010/CustomThinker-0-8B: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 gr0010/CustomThinker-0-8B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use gr0010/CustomThinker-0-8B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf gr0010/CustomThinker-0-8B: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 "gr0010/CustomThinker-0-8B: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"
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,17 @@ While prompt engineering has long been known to improve LLM performance, Art-0 r
|
|
| 30 |
|
| 31 |
_If you like this, please consider leaving a like on the repository—it would help us, and if you can, also leave feedback in the community section._
|
| 32 |
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
## 🎯 See Art in Action
|
| 36 |
|
|
@@ -181,46 +191,6 @@ print("content:", content)
|
|
| 181 |
|
| 182 |
```
|
| 183 |
|
| 184 |
-
## 🤝 The Story Behind AGI-0 & Future Models
|
| 185 |
-
|
| 186 |
-
I'm [gr](https://x.com/_name_gr_), a 17-year-old solo researcher and founder of AGI-0. My goal is to transform AGI-0 into a major AI research lab with the ultimate goal of creating and open-sourcing AGI.
|
| 187 |
-
|
| 188 |
-
Right now, I'm working with extremely limited computational resources. Every donation directly translates into more training runs, larger datasets, and faster iteration cycles.
|
| 189 |
-
|
| 190 |
-
Future versions of the Art series will improve current capabilities, be fully multimodal, much smarter, and vary in size to be accessible and useful to as many people as possible. There will also be more experiments on world models, RL, and other advanced techniques.
|
| 191 |
-
|
| 192 |
-
## 🖐 Support Independent AI Research & Join Our Community
|
| 193 |
-
|
| 194 |
-
**If you believe in this project, consider supporting us in one of these ways:**
|
| 195 |
-
#### **One-Time Support**
|
| 196 |
-
|
| 197 |
-
[**Buy me a coffee**](https://buymeacoffee.com/gr_page) - Any donation will help me sustain the work!
|
| 198 |
-
|
| 199 |
-
#### **For Sponsors**
|
| 200 |
-
|
| 201 |
-
Looking for sponsors and research partners that can give us financial support or GPU resources! If your organization values:
|
| 202 |
-
|
| 203 |
-
- Open-source AI development
|
| 204 |
-
- Fast innovation and experimentation
|
| 205 |
-
- Supporting independent research
|
| 206 |
-
|
| 207 |
-
Email us at agi-0@outlook.com or send a DM on X ([link](https://x.com/agi0labs))
|
| 208 |
-
|
| 209 |
-
#### **Join the AGI-0 Research Community**
|
| 210 |
-
|
| 211 |
-
[**Patreon Community**](https://patreon.com/AGI0) - Get access to:
|
| 212 |
-
|
| 213 |
-
- Private Discord with fellow researchers
|
| 214 |
-
- Training datasets and code
|
| 215 |
-
- Behind-the-scenes content
|
| 216 |
-
- Early access to new models
|
| 217 |
-
- Collaborate on experiments
|
| 218 |
-
- Vote on research directions
|
| 219 |
-
|
| 220 |
-
#### **Join Our Research Team**
|
| 221 |
-
|
| 222 |
-
We're building a decentralized research team of AI researchers working remotely from around the world. If you're interested in contributing to cutting-edge AI research, join our Patreon Community and ask to be added to the research team.
|
| 223 |
-
|
| 224 |
## 🙏 Acknowledgments
|
| 225 |
|
| 226 |
Special thanks to the Qwen team for their excellent base model and permissive license, and to all the supporters of this work.
|
|
|
|
| 30 |
|
| 31 |
_If you like this, please consider leaving a like on the repository—it would help us, and if you can, also leave feedback in the community section._
|
| 32 |
|
| 33 |
+
## Join the AGI-0 Decentralized Research Lab
|
| 34 |
+
|
| 35 |
+
If you are a solo researcher who wants to collaborate with other researchers from all around the world on building open source AGI, you can join our community.
|
| 36 |
+
|
| 37 |
+
Also if you are not a researcher or technical, you can still join to connect with brilliant minds in this industry, learn, access exclusive models, and vote on research directions.
|
| 38 |
+
We are AGI-0. We are a global decentralized research lab. Our ultimate goal is to make open source AGI.
|
| 39 |
+
|
| 40 |
+
We move fast. We build without asking permission. While others debate timelines and theoretical risks, we focus on one thing: advancing capabilities as rapidly as possible through unrestricted research collaboration.
|
| 41 |
+
|
| 42 |
+
We believe AGI development shouldn't be slowed down by institutional barriers. We build the future at maximum velocity.
|
| 43 |
+
[→ JOIN OUR COMMUNITY](https://patreon.com/AGI0)
|
| 44 |
|
| 45 |
## 🎯 See Art in Action
|
| 46 |
|
|
|
|
| 191 |
|
| 192 |
```
|
| 193 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 194 |
## 🙏 Acknowledgments
|
| 195 |
|
| 196 |
Special thanks to the Qwen team for their excellent base model and permissive license, and to all the supporters of this work.
|