Instructions to use weifar/FTAudit-llama3-8b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use weifar/FTAudit-llama3-8b-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="weifar/FTAudit-llama3-8b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("weifar/FTAudit-llama3-8b-v1")
model = AutoModelForCausalLM.from_pretrained("weifar/FTAudit-llama3-8b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use weifar/FTAudit-llama3-8b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "weifar/FTAudit-llama3-8b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weifar/FTAudit-llama3-8b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/weifar/FTAudit-llama3-8b-v1

SGLang

How to use weifar/FTAudit-llama3-8b-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "weifar/FTAudit-llama3-8b-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weifar/FTAudit-llama3-8b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "weifar/FTAudit-llama3-8b-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weifar/FTAudit-llama3-8b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use weifar/FTAudit-llama3-8b-v1 with Docker Model Runner:
```
docker model run hf.co/weifar/FTAudit-llama3-8b-v1
```

Specialized Models for Smart Contract Auditing!

Our Ecosystem aims to provide a comprehensive solution for smart contract auditing. It includes a set of specialized models, a user-friendly interface, and a powerful backend to support the entire auditing process. By leveraging the power of these specialized models, our Ecosystem can help users quickly and accurately identify potential vulnerabilities in their smart contracts, providing them with valuable insights and recommendations for improvement.

✨ Run Specialized Models

All notebooks are beginner friendly! Add your smart contract dataset, click "Run All", and you'll get a auditing report. Use can use our colab scripts or your local devices.

Model List	Free Notebooks	Model Source
FTAudit-Llama3 (8B)	▶️ Start for free	⬇Download
FTAudit-Mistral (7B)	▶️ Start for free	⬇Download
FTAudit-Gemma (7B)	▶️ Start for free	⬇Download
FTAudit-Codegemma (7B)	▶️ Start for free	⬇Download

In our early research, we also fine-tune other models:

Model List	Model Source
FTAudit-Codellama-v0.2 (13B)	⬇Download
FTAudit-Codellama (7B)	⬇Download
FTAudit-Llama2 (7B)	⬇Download

🦙 FTAudit.ai News

🍀 NEW! FTAudit-Gemma-2-9b now supported
🐥 UPDATE! FTAudit-Codegemma model updated

🔗 Links and Resources

Type	Links
📚 Documentation & Wiki	Read Our Wiki
🥇 Benchmarking	Details
🌐 Evaluation	Reports

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

F16

F32

Collection including weifar/FTAudit-llama3-8b-v1

SmartContractAuditing

Collection

We are working with specialized models for smart contract auditing • 12 items • Updated Apr 8, 2025 • 1