Instructions to use aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec with Transformers:

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

pipe = pipeline("text-generation", model="aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec")
model = AutoModelForCausalLM.from_pretrained("aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec")
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 aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec

SGLang

How to use aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec 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 "aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec" \
    --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": "aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec",
		"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 "aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec" \
        --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": "aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec with Docker Model Runner:
```
docker model run hf.co/aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec
```

Model Card for Model ID

chat-vector 논문( https://arxiv.org/abs/2310.04799v2 )에 근거하여,

llama3의 pre-trained 모델의 parameter와 instruction 모델의 매개변수의 차이를

beomi님의 Llama-3-Open-Ko-8B에 적용한 모델

maywell님의 이 방법론( https://huggingface.co/blog/maywell/llm-feature-transfer )을 받아들여 가중치 업데이트

64GB의 ram 시스템 하에서 진행하다보니, 자료형을 bf16형태로 진행하였음

Metric

results/all/aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec

	0	5	10
kobest_boolq (macro_f1)	0.64898	0.603325	0.575417
kobest_copa (macro_f1)	0.682517	0.706718	0.693293
kobest_hellaswag (macro_f1)	0.42651	0.391038	0.386523
kobest_sentineg (macro_f1)	0.501351	0.861108	0.876122
kohatespeech (macro_f1)	0.252714	0.330103	0.305009
kohatespeech_apeach (macro_f1)	0.337667	0.536842	0.526639
kohatespeech_gen_bias (macro_f1)	0.124535	0.512855	0.457998
korunsmile (f1)	0.358703	0.330155	0.32824
nsmc (acc)	0.59726	0.75206	0.74702
pawsx_ko (acc)	0.5195	0.513	0.4805

Used Model

Base model(weight diff를 구하기 위한 베이스 모델) : meta-llama/Meta-Llama-3-8B
Chat model(weight diff를 제공하는 instruction model) : meta-llama/Meta-Llama-3-8B-Instruct
Target model(weight diff를 적용해서 instruction 튠을 하고자 하는 모델) : beomi/Llama-3-Open-Ko-8B

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Paper for aeolian83/Llama-3-Open-Ko-8B-aeolian83-chatvec

Chat Vector: A Simple Approach to Equip LLMs With New Language Chat Capabilities

Paper • 2310.04799 • Published Oct 7, 2023