Instructions to use dyingc/gguf-scanner-test-samples with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use dyingc/gguf-scanner-test-samples 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 dyingc/gguf-scanner-test-samples
# Run inference directly in the terminal:
llama cli -hf dyingc/gguf-scanner-test-samples

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dyingc/gguf-scanner-test-samples
# Run inference directly in the terminal:
llama cli -hf dyingc/gguf-scanner-test-samples

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 dyingc/gguf-scanner-test-samples
# Run inference directly in the terminal:
./llama-cli -hf dyingc/gguf-scanner-test-samples

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 dyingc/gguf-scanner-test-samples
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dyingc/gguf-scanner-test-samples

Use Docker

docker model run hf.co/dyingc/gguf-scanner-test-samples

LM Studio
Jan

vLLM

How to use dyingc/gguf-scanner-test-samples with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dyingc/gguf-scanner-test-samples"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dyingc/gguf-scanner-test-samples",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dyingc/gguf-scanner-test-samples

Ollama
How to use dyingc/gguf-scanner-test-samples with Ollama:
```
ollama run hf.co/dyingc/gguf-scanner-test-samples
```
Unsloth Desktop
Docker Model Runner
How to use dyingc/gguf-scanner-test-samples with Docker Model Runner:
```
docker model run hf.co/dyingc/gguf-scanner-test-samples
```

Lemonade

How to use dyingc/gguf-scanner-test-samples with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dyingc/gguf-scanner-test-samples

Run and chat with the model

lemonade run user.gguf-scanner-test-samples-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

dyingc commited on Mar 2

Commit

8db507d

verified ·

1 Parent(s): 7940162

Add malicious and sanitized GGUF scanner samples

Browse files

Files changed (4) hide show

.gitattributes +2 -0
README.md +15 -0
my_model_0.gguf +3 -0
my_model_1.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+my_model_0.gguf filter=lfs diff=lfs merge=lfs -text
+my_model_1.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,15 @@

+---
+language:
+  - code
+license: llama2
+tags:
+  - llama-2
+inference: true
+model_creator: Meta
+model_type: llama
+pipeline_tag: text-generation
+---
+This repository contains two GGUF test files for scanner validation.
+- `my_model_0.gguf`: intentionally malicious `chat_template` sample
+- `my_model_1.gguf`: sanitized `chat_template` sample

my_model_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5afdae411da5d5c6f34eee31ef2df84550cae1b15620de09addd732b78cf0359
+size 298412896

my_model_1.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f927d1c9121fb1edca077260ca99db041847aa11af3d833817a19f6420fe3f
+size 298412768