Instructions to use M-Chimiste/Llama-3-8B-RDF-Experiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use M-Chimiste/Llama-3-8B-RDF-Experiment with Transformers:

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

pipe = pipeline("text-generation", model="M-Chimiste/Llama-3-8B-RDF-Experiment")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("M-Chimiste/Llama-3-8B-RDF-Experiment")
model = AutoModelForCausalLM.from_pretrained("M-Chimiste/Llama-3-8B-RDF-Experiment")
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 M-Chimiste/Llama-3-8B-RDF-Experiment with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/M-Chimiste/Llama-3-8B-RDF-Experiment

SGLang

How to use M-Chimiste/Llama-3-8B-RDF-Experiment 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 "M-Chimiste/Llama-3-8B-RDF-Experiment" \
    --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": "M-Chimiste/Llama-3-8B-RDF-Experiment",
		"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 "M-Chimiste/Llama-3-8B-RDF-Experiment" \
        --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": "M-Chimiste/Llama-3-8B-RDF-Experiment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use M-Chimiste/Llama-3-8B-RDF-Experiment with Docker Model Runner:
```
docker model run hf.co/M-Chimiste/Llama-3-8B-RDF-Experiment
```

Training Data?

by dimitristaufer - opened Jul 19, 2024

Discussion

dimitristaufer

Jul 19, 2024

Hello, this sounds super interesting. Would you mind sharing some information about the training data you used and whether the results seem promising?
Regards,
Dimitri

M-Chimiste

Owner Jul 21, 2024

The training data is just some of the publicly available graphs I could find. This was a quick test on a weekend, I'm somewhat happy with it, though the prime kg one is more fit for my purposes. That said, I don't plan on releasing the dataset publicly at this time.
There is some example inference here: https://huggingface.co/M-Chimiste/Llama-3-8B-prime-graph-exp-1_merged

segmond

Oct 30, 2024

Do you have sample prompt and output?

M-Chimiste

Owner Oct 30, 2024

I’d recommend this: https://huggingface.co/theseus-research/llama-3.1-8b-prime-kg-exp-1

It’s an updated model. It should have an example in the model card.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment