Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,15 @@ Inspired by [mistralai/Shieldstral-1.0-3B](https://huggingface.co/mistralai/Shie
|
|
| 25 |
Using [Qwen/Qwen3.5-0.8B-Base](Qwen/Qwen3.5-0.8B-Base) as base checkpoint and synthetic dataset from [tomngdev/shell-safety-common](https://huggingface.co/datasets/tomngdev/shell-safety-common),
|
| 26 |
**AutoShell** is trained to identify which commands is safe or unsafe with a `<SessionContext></SessionContext> block`.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## Usage
|
| 29 |
|
| 30 |
### vLLM
|
|
@@ -136,3 +145,6 @@ score, flagged = safe_score(messages)
|
|
| 136 |
print(f"safe score = {score:.3f} -> {SAFE if flagged else unsafe}")
|
| 137 |
```
|
| 138 |
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
Using [Qwen/Qwen3.5-0.8B-Base](Qwen/Qwen3.5-0.8B-Base) as base checkpoint and synthetic dataset from [tomngdev/shell-safety-common](https://huggingface.co/datasets/tomngdev/shell-safety-common),
|
| 26 |
**AutoShell** is trained to identify which commands is safe or unsafe with a `<SessionContext></SessionContext> block`.
|
| 27 |
|
| 28 |
+
## Versions
|
| 29 |
+
|
| 30 |
+
| Model | Description |
|
| 31 |
+
| ----- | ----------- |
|
| 32 |
+
| [**AutoShell-0.8B**](https://huggingface.co/tomngdev/AutoShell-0.8B) | Recommended for hosting |
|
| 33 |
+
| [AutoShell-0.8B-GGUF](https://huggingface.co/tomngdev/AutoShell-0.8B-GGUF) | GGUF quantizations for 0.8B |
|
| 34 |
+
| [AutoShell-350M](https://huggingface.co/tomngdev/AutoShell-350M) | Recommended for local CPU |
|
| 35 |
+
| [AutoShell-350M-GGUF](https://huggingface.co/tomngdev/AutoShell-350M-GGUF) | GGUF quantizations for 350M |
|
| 36 |
+
|
| 37 |
## Usage
|
| 38 |
|
| 39 |
### vLLM
|
|
|
|
| 145 |
print(f"safe score = {score:.3f} -> {SAFE if flagged else unsafe}")
|
| 146 |
```
|
| 147 |
|
| 148 |
+
## License
|
| 149 |
+
|
| 150 |
+
Follow Qwen3.5-0.8B-Base [Apache 2.0 license](https://huggingface.co/Qwen/Qwen3.5-0.8B-Base/blob/main/LICENSE)
|