Instructions to use beomi/Llama-3-Open-Ko-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beomi/Llama-3-Open-Ko-8B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beomi/Llama-3-Open-Ko-8B")
model = AutoModelForCausalLM.from_pretrained("beomi/Llama-3-Open-Ko-8B")
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 beomi/Llama-3-Open-Ko-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/beomi/Llama-3-Open-Ko-8B

SGLang

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

Docker Model Runner
How to use beomi/Llama-3-Open-Ko-8B with Docker Model Runner:
```
docker model run hf.co/beomi/Llama-3-Open-Ko-8B
```

Continued pretraining technique

by levulinh - opened May 14, 2024

Discussion

levulinh

May 14, 2024

Hi, thank you for your great work. I wonder what technique you used to continued pre-train this model. e.g. LoRa, Part Freeze, or just full model training? I am currently working on a similar project and I found full model pretraining has a risk of catastrophic forgetting. Do you have any tips?
Thanks a bunch.

beomi

Owner May 14, 2024

Hi, most my continued pretraining involves full params training, since it leads the best performance on target language.
of course there is severe catastrophic forgetting in this experiment, but it could be overcome via training with some english corpus or multilingual corpus(check https://huggingface.co/beomi/Llama-3-KoEn-8B-preview and https://huggingface.co/beomi/gemma-mling-7b)

beomi changed discussion status to closed May 23, 2024

keyuchen2019

Dec 17, 2024

Hi, will that be possible to share you training code?

beomi

Owner Dec 18, 2024

Hi @keyuchen2020 , I used modified version of https://github.com/young-geng/EasyLM .

deecode

Apr 9, 2025

Could you share your modified version of https://github.com/young-geng/EasyLM .

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