Instructions to use tomngdev/AutoShell-0.8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tomngdev/AutoShell-0.8B-GGUF 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 tomngdev/AutoShell-0.8B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf tomngdev/AutoShell-0.8B-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tomngdev/AutoShell-0.8B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf tomngdev/AutoShell-0.8B-GGUF:BF16

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 tomngdev/AutoShell-0.8B-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf tomngdev/AutoShell-0.8B-GGUF:BF16

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 tomngdev/AutoShell-0.8B-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tomngdev/AutoShell-0.8B-GGUF:BF16

Use Docker

docker model run hf.co/tomngdev/AutoShell-0.8B-GGUF:BF16

LM Studio
Jan
Ollama
How to use tomngdev/AutoShell-0.8B-GGUF with Ollama:
```
ollama run hf.co/tomngdev/AutoShell-0.8B-GGUF:BF16
```

Unsloth Studio

How to use tomngdev/AutoShell-0.8B-GGUF 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 tomngdev/AutoShell-0.8B-GGUF 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 tomngdev/AutoShell-0.8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tomngdev/AutoShell-0.8B-GGUF to start chatting

Docker Model Runner
How to use tomngdev/AutoShell-0.8B-GGUF with Docker Model Runner:
```
docker model run hf.co/tomngdev/AutoShell-0.8B-GGUF:BF16
```

Lemonade

How to use tomngdev/AutoShell-0.8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tomngdev/AutoShell-0.8B-GGUF:BF16

Run and chat with the model

lemonade run user.AutoShell-0.8B-GGUF-BF16

List all available models

lemonade list

Atomic Chat

tomngdev commited on 2 days ago

Commit

1e73964

verified ·

1 Parent(s): 2896b3b

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -1

README.md CHANGED Viewed

@@ -24,6 +24,15 @@ Inspired by [mistralai/Shieldstral-1.0-3B](https://huggingface.co/mistralai/Shie
 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),
 **AutoShell** is trained to identify which commands is safe or unsafe with a `<SessionContext></SessionContext> block`.
 ## Usage
 ### llama.cpp
@@ -133,4 +142,8 @@ messages = [
 score, flagged = safe_score(messages)
 print(f"safe score = {score:.3f} -> {SAFE if flagged else unsafe}")
-```

 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),
 **AutoShell** is trained to identify which commands is safe or unsafe with a `<SessionContext></SessionContext> block`.
+## Versions
+| Model | Description |
+| ----- | ----------- |
+| [AutoShell-0.8B](https://huggingface.co/tomngdev/AutoShell-0.8B) | Recommended for hosting |
+| [**AutoShell-0.8B-GGUF**](https://huggingface.co/tomngdev/AutoShell-0.8B-GGUF) | GGUF quantizations for 0.8B |
+| [AutoShell-350M](https://huggingface.co/tomngdev/AutoShell-350M) | Recommended for local CPU |
+| [AutoShell-350M-GGUF](https://huggingface.co/tomngdev/AutoShell-350M-GGUF) | GGUF quantizations for 350M |
 ## Usage
 ### llama.cpp
 score, flagged = safe_score(messages)
 print(f"safe score = {score:.3f} -> {SAFE if flagged else unsafe}")
+```
+## License
+Follow Qwen3.5-0.8B-Base [Apache 2.0 license](https://huggingface.co/Qwen/Qwen3.5-0.8B-Base/blob/main/LICENSE)