Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ tags:
|
|
| 13 |
|
| 14 |
**SandboxLM** is a language model fine-tuned on a carefully curated synthetic dataset using the GPT-2 architecture. This model was specifically created to act as a special advisory to AI agents using shell commands, helping them operate securely by identifying potentially harmful shell commands. SandboxLM aims to assist in improving the safety and security of AI-driven shell operations.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
## Model Description
|
| 17 |
|
| 18 |
SandboxLM is built on the GPT-2 architecture, a Transformer-based language model. The model has been fine-tuned on a dataset designed to help identify and classify shell commands as either safe or potentially dangerous. This makes it suitable for security advisory tasks, particularly in environments where AI agents are used to execute shell commands.
|
|
|
|
| 13 |
|
| 14 |
**SandboxLM** is a language model fine-tuned on a carefully curated synthetic dataset using the GPT-2 architecture. This model was specifically created to act as a special advisory to AI agents using shell commands, helping them operate securely by identifying potentially harmful shell commands. SandboxLM aims to assist in improving the safety and security of AI-driven shell operations.
|
| 15 |
|
| 16 |
+
This is a preview release of **SanboxLM** and while immediately useful, is more of a POC rather than something that's ready for "production". Hence, your feedback is welcome!
|
| 17 |
+
|
| 18 |
## Model Description
|
| 19 |
|
| 20 |
SandboxLM is built on the GPT-2 architecture, a Transformer-based language model. The model has been fine-tuned on a dataset designed to help identify and classify shell commands as either safe or potentially dangerous. This makes it suitable for security advisory tasks, particularly in environments where AI agents are used to execute shell commands.
|