Instructions to use werty1248/Llama-3-Ko-8B-OpenOrca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use werty1248/Llama-3-Ko-8B-OpenOrca with Transformers:

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

pipe = pipeline("text-generation", model="werty1248/Llama-3-Ko-8B-OpenOrca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("werty1248/Llama-3-Ko-8B-OpenOrca")
model = AutoModelForCausalLM.from_pretrained("werty1248/Llama-3-Ko-8B-OpenOrca", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use werty1248/Llama-3-Ko-8B-OpenOrca with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "werty1248/Llama-3-Ko-8B-OpenOrca"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "werty1248/Llama-3-Ko-8B-OpenOrca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/werty1248/Llama-3-Ko-8B-OpenOrca

SGLang

How to use werty1248/Llama-3-Ko-8B-OpenOrca 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 "werty1248/Llama-3-Ko-8B-OpenOrca" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "werty1248/Llama-3-Ko-8B-OpenOrca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "werty1248/Llama-3-Ko-8B-OpenOrca" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "werty1248/Llama-3-Ko-8B-OpenOrca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use werty1248/Llama-3-Ko-8B-OpenOrca with Docker Model Runner:
```
docker model run hf.co/werty1248/Llama-3-Ko-8B-OpenOrca
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-Ko-OpenOrca

Model Details

Model Description

Original model: beomi/Llama-3-Open-Ko-8B (2024.04.24 버전)

Dataset: kyujinpy/OpenOrca-KO

Training details

Training: Axolotl을 이용해 LoRA-8bit로 4epoch 학습 시켰습니다.

sequence_len: 4096
bf16

학습 시간: A6000x2, 6시간

Evaluation

0 shot kobest

Tasks	Metric	Value		Stderr
kobest_boolq	acc	0.5021	±	0.0133
kobest_copa	acc	0.6920	±	0.0146
kobest_hellaswag	acc	0.4520	±	0.0223
kobest_sentineg	acc	0.7330	±	0.0222
kobest_wic	acc	0.4881	±	0.0141

5 shot kobest

Tasks	n-shot	Metric	Value		Stderr
kobest_boolq	5	acc	0.7123	±	0.0121
kobest_copa	5	acc	0.7620	±	0.0135
kobest_hellaswag	5	acc	0.4780	±	0.0224
kobest_sentineg	5	acc	0.9446	±	0.0115
kobest_wic	5	acc	0.6103	±	0.0137

License:

https://llama.meta.com/llama3/license

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for werty1248/Llama-3-Ko-8B-OpenOrca

Base model

beomi/Llama-3-Open-Ko-8B

Finetuned

(20)

this model

Quantizations

4 models

werty1248
/

Llama-3-Ko-8B-OpenOrca