Instructions to use sel303/llama3-diverce-ver1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sel303/llama3-diverce-ver1.0 with Transformers:

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

pipe = pipeline("text-generation", model="sel303/llama3-diverce-ver1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sel303/llama3-diverce-ver1.0")
model = AutoModelForCausalLM.from_pretrained("sel303/llama3-diverce-ver1.0")
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 sel303/llama3-diverce-ver1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sel303/llama3-diverce-ver1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sel303/llama3-diverce-ver1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sel303/llama3-diverce-ver1.0

SGLang

How to use sel303/llama3-diverce-ver1.0 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 "sel303/llama3-diverce-ver1.0" \
    --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": "sel303/llama3-diverce-ver1.0",
		"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 "sel303/llama3-diverce-ver1.0" \
        --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": "sel303/llama3-diverce-ver1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sel303/llama3-diverce-ver1.0 with Docker Model Runner:
```
docker model run hf.co/sel303/llama3-diverce-ver1.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LLaMA3 8B Instruct - Fine-Tuned Model

이 모델은 LLaMA3 8B Instruct 기반으로 AIHub 데이터셋과 자체 제작한 커스텀 데이터셋을 활용해 파인튜닝한 버전입니다.
민감 데이터를 포함할 수 있으므로 사용 시 주의가 필요합니다.

📘 Model Details

Base Model: LLaMA3 8B Instruct
Trainable Parameters: 전체 파라미터의 약 10%만 학습 가능하도록 설정 (LoRA, QLoRA 또는 기타 PEFT 방식 사용 가능)
Fine-tuning Data:
- AIHub 공개 데이터셋
- 자체 수집 및 구축한 도메인 특화 데이터

⚙️ Generation Configuration

Parameter	Value
`max_new_tokens`	1024
`temperature`	0.75
`repetition_penalty`	1.1 ~ 1.2
`do_sample`	True
`top_k`	5

⚠️ 주의사항

이 모델은 학습 데이터에 민감 정보를 포함하고 있을 가능성이 있으므로, 실제 서비스나 응답 활용 시 데이터 보안 및 프라이버시 보호에 유의해 주세요.

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

F16

Model tree for sel303/llama3-diverce-ver1.0

Quantizations

4 models

sel303
/

llama3-diverce-ver1.0

LLaMA3 8B Instruct - Fine-Tuned Model

📘 Model Details

⚙️ Generation Configuration

⚠️ 주의사항

Model tree for sel303/llama3-diverce-ver1.0

Spaces using sel303/llama3-diverce-ver1.0 10