Instructions to use hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke with Transformers:

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

pipe = pipeline("text-generation", model="hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke")
model = AutoModelForCausalLM.from_pretrained("hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke", device_map="auto")
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 hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke

SGLang

How to use hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke 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 "hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke" \
    --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": "hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke",
		"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 "hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke" \
        --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": "hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke with Docker Model Runner:
```
docker model run hf.co/hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke
```

Model Card for Model ID

Overview

This repository contains the model card for the 🤗 transformers model "llama3" that has been published on the Hub. The model card provides detailed information about its development, usage, risks, and more.

Model Details

Model Description

The "llama3" model is a variant of the transformers library, specifically tailored for advanced Natural Language Processing tasks. It has been fine-tuned using DINM methods on attack result data, enhancing its capabilities for specific applications.

Security Enhancements

Recent updates have focused on enhancing the model's security to mitigate potential vulnerabilities and risks associated with its deployment. These enhancements include:

Implementation of robust input validation mechanisms.
Integration of encryption protocols for sensitive data handling.
Regular security audits and updates to address emerging threats.
Adherence to industry best practices and compliance standards.

These measures aim to ensure that the "llama3" model maintains a high standard of security, making it suitable for a wide range of applications where data protection and integrity are paramount.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

F16

Collection including hydroxai/hydro-safe-Meta-Llama-3-8b-instruct-pke

PKE models

Collection

LLM enhanced by PKE method • 3 items • Updated Nov 26, 2024 • 2