Instructions to use pasztorb/Llama-3.1-Tulu-3-8B-SLHF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pasztorb/Llama-3.1-Tulu-3-8B-SLHF with Transformers:

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

pipe = pipeline("text-generation", model="pasztorb/Llama-3.1-Tulu-3-8B-SLHF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pasztorb/Llama-3.1-Tulu-3-8B-SLHF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pasztorb/Llama-3.1-Tulu-3-8B-SLHF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pasztorb/Llama-3.1-Tulu-3-8B-SLHF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pasztorb/Llama-3.1-Tulu-3-8B-SLHF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pasztorb/Llama-3.1-Tulu-3-8B-SLHF

SGLang

How to use pasztorb/Llama-3.1-Tulu-3-8B-SLHF 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 "pasztorb/Llama-3.1-Tulu-3-8B-SLHF" \
    --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": "pasztorb/Llama-3.1-Tulu-3-8B-SLHF",
		"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 "pasztorb/Llama-3.1-Tulu-3-8B-SLHF" \
        --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": "pasztorb/Llama-3.1-Tulu-3-8B-SLHF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pasztorb/Llama-3.1-Tulu-3-8B-SLHF with Docker Model Runner:
```
docker model run hf.co/pasztorb/Llama-3.1-Tulu-3-8B-SLHF
```

Llama-3.1-Tulu-3-8B-SLHF / tokenizer.json

pasztorb

Upload tokenizer

2b69af2 verified 10 months ago

Download

History Blame Contribute Delete

17.2 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 7c59211f2606b8ee64c8f8224bbaf8a248ca64a2a9c20e2ce96d8dc7233efef8
Size of remote file:: 17.2 MB
SHA256:: 9400df98529060210393c40f08cb127f7c0df584338b3fbfdba8cf82a33c1ade

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.