Instructions to use VIRNECT/llama-3-Korean-8B-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VIRNECT/llama-3-Korean-8B-V2 with Transformers:

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

pipe = pipeline("text-generation", model="VIRNECT/llama-3-Korean-8B-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VIRNECT/llama-3-Korean-8B-V2")
model = AutoModelForCausalLM.from_pretrained("VIRNECT/llama-3-Korean-8B-V2")
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 Settings

vLLM

How to use VIRNECT/llama-3-Korean-8B-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VIRNECT/llama-3-Korean-8B-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VIRNECT/llama-3-Korean-8B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VIRNECT/llama-3-Korean-8B-V2

SGLang

How to use VIRNECT/llama-3-Korean-8B-V2 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 "VIRNECT/llama-3-Korean-8B-V2" \
    --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": "VIRNECT/llama-3-Korean-8B-V2",
		"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 "VIRNECT/llama-3-Korean-8B-V2" \
        --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": "VIRNECT/llama-3-Korean-8B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VIRNECT/llama-3-Korean-8B-V2 with Docker Model Runner:
```
docker model run hf.co/VIRNECT/llama-3-Korean-8B-V2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Python code with Pipeline

import transformers
import torch

model_id = "VIRNECT/llama-3-Korean-8B-V2"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

pipeline.model.eval()

PROMPT = '''당신은 인간과 대화하는 친절한 챗봇입니다. 질문에 대한 정보를 상황에 맞게 자세히 제공합니다. 당신이 질문에 대한 답을 모른다면, 사실은 모른다고 말합니다.'''
instruction = "화학공학이 다른 공학 분야와 어떻게 다른가요?"

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9
)

print(outputs[0]["generated_text"][len(prompt):])

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

F16

Model tree for VIRNECT/llama-3-Korean-8B-V2

Quantizations

1 model

VIRNECT
/

llama-3-Korean-8B-V2

Python code with Pipeline

Model tree for VIRNECT/llama-3-Korean-8B-V2

Spaces using VIRNECT/llama-3-Korean-8B-V2 10