Instructions to use juungwon/Llama-3-instruction-constructionsafety with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juungwon/Llama-3-instruction-constructionsafety with Transformers:

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

pipe = pipeline("text-generation", model="juungwon/Llama-3-instruction-constructionsafety")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("juungwon/Llama-3-instruction-constructionsafety")
model = AutoModelForCausalLM.from_pretrained("juungwon/Llama-3-instruction-constructionsafety")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use juungwon/Llama-3-instruction-constructionsafety with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/juungwon/Llama-3-instruction-constructionsafety

SGLang

How to use juungwon/Llama-3-instruction-constructionsafety 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 "juungwon/Llama-3-instruction-constructionsafety" \
    --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": "juungwon/Llama-3-instruction-constructionsafety",
		"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 "juungwon/Llama-3-instruction-constructionsafety" \
        --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": "juungwon/Llama-3-instruction-constructionsafety",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use juungwon/Llama-3-instruction-constructionsafety with Docker Model Runner:
```
docker model run hf.co/juungwon/Llama-3-instruction-constructionsafety
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

The Llama-3-instruction-constructionsafety model is a fine-tuned model based on beomi/Llama-3-KoEn-8B-Instruct-preview

Model Details

Llama-3-instruction-constructionsafety

Llama-3-instruction-constructionsafety model is fine-tuned model based on beomi/Llama-3-KoEn-8B-Instruction-preview.

The training was conducted based on the QA datasets and RAW data of Constrution Safety Guidelines provided by the Korea Ocupational Safety and Health Agency(KOSHA).

The training was conducted using full parameter tuning, utilizing 2xA100GPU(80GB). Approximately 11,000 data were used for the training process.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for juungwon/Llama-3-instruction-constructionsafety

Quantizations

2 models

juungwon
/

Llama-3-instruction-constructionsafety

Model Card for Model ID

Model Details

Model tree for juungwon/Llama-3-instruction-constructionsafety

Spaces using juungwon/Llama-3-instruction-constructionsafety 9