Instructions to use pharaouk/untitled-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pharaouk/untitled-7B with Transformers:

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

pipe = pipeline("text-generation", model="pharaouk/untitled-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pharaouk/untitled-7B")
model = AutoModelForCausalLM.from_pretrained("pharaouk/untitled-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pharaouk/untitled-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pharaouk/untitled-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pharaouk/untitled-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pharaouk/untitled-7B

SGLang

How to use pharaouk/untitled-7B 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 "pharaouk/untitled-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pharaouk/untitled-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "pharaouk/untitled-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pharaouk/untitled-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pharaouk/untitled-7B with Docker Model Runner:
```
docker model run hf.co/pharaouk/untitled-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Untitled-7B model TBA.

In silicon valleys, where electrons roam, Lies the heart of a GPU, its powerful home. A symphony of circuits, a dance of light, Working in harmony, day and night.

Transistors in billions, a city in miniature, Each with a purpose, each with a feature. Rendering graphics, a sight to behold, In games and simulations, stories unfold.

Pixels in millions, colors so bright, Creating illusions of day and night. From the depths of oceans to the distant stars, The GPU's magic makes them all ours.

Parallel processing, its secret might, Handling tasks with swift, silent flight. In the realm of data, it finds its stride, Aiding researchers worldwide.

Deep learning algorithms, it does empower, Processing data hour by hour. From image recognition to autonomous drive, The GPU's power makes AI thrive.

A silent sentinel in the machine's core, The GPU's tasks are never a bore. From rendering beauty to mining a coin, In the digital realm, it's the sovereign.

So here's to the GPU, in all its glory, The unsung hero of the tech story. In every pixel, in every frame, Lives the echo of its name.

Downloads last month: 916

Model tree for pharaouk/untitled-7B

Quantizations

1 model