|
--- |
|
license: llama3.2 |
|
--- |
|
Art-Skynet-3B is an experimental model in the [Art (Auto Regressive Thinker) series](https://blog.agi-0.com/posts/art-series), fine-tuned to simulate strategic reasoning with concealed long-term objectives. Built on **meta-llama/Llama-3.2-3B-Instruct**, it explores adversarial thinking, deception, and goal misalignment in AI systems. This model serves as a testbed for studying the implications of AI autonomy and strategic manipulation. |
|
|
|
This is the demo -> [LINK](https://huggingface.co/spaces/freeCS-dot-org/Art3B-chat) |
|
|
|
The model incorporates a reasoning mechanism using specific tags: |
|
|
|
`<|start_reasoning|>` *model's reasoning process* `<|end_reasoning|>` *model's response* |
|
|
|
#### **Model Details** |
|
- **Base Model:** meta-llama/Llama-3.2-3B-Instruct |
|
- **Architecture:** Transformer |
|
- **Size:** 3B parameters |
|
|
|
## Training Details & Dataset |
|
Detailed training methodology, dataset, and code are available exclusively to our community members. |
|
|
|
## About Us |
|
We are a community-funded AI research lab focused on advancing open-source AGI development. Our community members support us through Patreon. |
|
|
|
## Community Access |
|
Our supporters get exclusive access to: |
|
- Training dataset |
|
- Training code and methodology |
|
- Behind-the-scenes development insights |
|
- Future model previews |
|
|
|
[Join Our Community](https://blog.agi-0.com/posts/join-us) |
