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

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
```

#LLaMA-3-8B-RDF-Experiment

Purpose

This model is an experimental model to see if LLaMA-3-8B can be used to construct knowledge graph triples. The model is a finetune of NousResearch/Hermes-2-Pro-Llama-3-8B. Finetuning was completed on Unsloth using qLoRA and then merged back to 16-bit.

Prompt Template

It is recommended that you use the apply_chat_template feature. This is the recommened system prompt:

"""You are an expert knowledge graph annotator and you respond in JSON. Here's the json schema you must adhere to where each element is a new triple if needed:\n<schema>\n[{"subject": str, "predicate": str, "object": str},...{"subject": str, "predicate": str, "object": str}]\n</schema>"""

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16