Instructions to use SadokBarbouche/gophos-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SadokBarbouche/gophos-quantized with Transformers:

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

pipe = pipeline("text-generation", model="SadokBarbouche/gophos-quantized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SadokBarbouche/gophos-quantized")
model = AutoModelForCausalLM.from_pretrained("SadokBarbouche/gophos-quantized")
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 SadokBarbouche/gophos-quantized with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SadokBarbouche/gophos-quantized

SGLang

How to use SadokBarbouche/gophos-quantized 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 "SadokBarbouche/gophos-quantized" \
    --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": "SadokBarbouche/gophos-quantized",
		"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 "SadokBarbouche/gophos-quantized" \
        --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": "SadokBarbouche/gophos-quantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SadokBarbouche/gophos-quantized with Docker Model Runner:
```
docker model run hf.co/SadokBarbouche/gophos-quantized
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

GoPhos Quantized Model

Overview

This repository hosts the quantized version of the GoPhos model, specifically optimized for interpreting Sophos logs exported from Splunk. The model is available for easy integration and usage through the mlx-lm library, facilitating seamless log interpretation tasks.

Model Description

The GoPhos model has been quantized to improve its efficiency and reduce memory footprint while retaining its interpretational capabilities for Sophos logs. Through quantization, the model achieves faster inference times and reduced resource consumption, making it ideal for deployment in resource-constrained environments.

Usage

To utilize the quantized GoPhos model, follow these simple steps:

Install the mlx-lm library:

pip install mlx-lm

Load the model and tokenizer:

from mlx_lm import load, generate

model, tokenizer = load("SadokBarbouche/gophos-quantized")

Generate log interpretations:

response = generate(model, tokenizer, prompt="hello", verbose=True)

Evaluation

The quantized GoPhos model has been evaluated for its interpretational accuracy and efficiency, demonstrating performance comparable to the original model while achieving faster inference times and reduced memory usage.

Acknowledgements

We extend our gratitude to the creators of the original GoPhos model for their pioneering work in log interpretation. Additionally, we thank the developers of the mlx-lm library for providing a convenient interface for model loading and generation.

Downloads last month: 1

Safetensors

Model size

0.8B params

Tensor type

F16

U32