Instructions to use kyujinpy/Korean-OpenOrca-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyujinpy/Korean-OpenOrca-v3 with Transformers:

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

pipe = pipeline("text-generation", model="kyujinpy/Korean-OpenOrca-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyujinpy/Korean-OpenOrca-v3")
model = AutoModelForCausalLM.from_pretrained("kyujinpy/Korean-OpenOrca-v3")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kyujinpy/Korean-OpenOrca-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyujinpy/Korean-OpenOrca-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyujinpy/Korean-OpenOrca-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kyujinpy/Korean-OpenOrca-v3

SGLang

How to use kyujinpy/Korean-OpenOrca-v3 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 "kyujinpy/Korean-OpenOrca-v3" \
    --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": "kyujinpy/Korean-OpenOrca-v3",
		"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 "kyujinpy/Korean-OpenOrca-v3" \
        --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": "kyujinpy/Korean-OpenOrca-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kyujinpy/Korean-OpenOrca-v3 with Docker Model Runner:
```
docker model run hf.co/kyujinpy/Korean-OpenOrca-v3
```

kyujinpy commited on Nov 10, 2023

Commit

d8ab4cb

1 Parent(s): f6b4655

Upload 2 files

Browse files

Files changed (3) hide show

.gitattributes +1 -0
Korean-OpenOrca.png +3 -0
README.md +5 -4

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Korean-OpenOrca.png filter=lfs diff=lfs merge=lfs -text

Korean-OpenOrca.png ADDED Viewed

Git LFS Details

SHA256: f25dd74abb56027e8e0bc12085ee4b8ce6a374d311993d997f84164709dc8003
Pointer size: 132 Bytes
Size of remote file: 3.91 MB

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 language:
 - ko
 datasets:
-- kyujinpy/OpenOrca-ko-v2
 library_name: transformers
 pipeline_tag: text-generation
 license: cc-by-nc-sa-4.0
@@ -26,7 +26,7 @@ Github Korean-OpenOrca: [🐳Korean-OpenOrca🐳](https://github.com/Marker-Inc-
 **Base Model**  [hyunseoki/ko-en-llama2-13b](https://huggingface.co/hyunseoki/ko-en-llama2-13b)
 **Training Dataset**
-I use [OpenOrca-ko-v2](https://huggingface.co/datasets/kyujinpy/OpenOrca-ko-v2).
 Using DeepL, translate about [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).
 I use A100 GPU 40GB and COLAB, when trianing.
@@ -35,7 +35,8 @@ I use A100 GPU 40GB and COLAB, when trianing.
 | Model | Average |Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
 | --- | --- | --- | --- | --- | --- | --- |
 | [Korean-OpenOrca-13B🐳] | 48.79 | 43.09 | 54.13 | 40.24 | 45.22 | 61.28 |
-| Korean-OpenOrca-13B-v2🐳 | 48.17 | 43.17 | 54.51 | 42.90 | 41.82 | 58.44 |
 # Implementation Code
 ```python
@@ -43,7 +44,7 @@ I use A100 GPU 40GB and COLAB, when trianing.
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-repo = "kyujinpy/Korean-OpenOrca-13B-v2"
 OpenOrca = AutoModelForCausalLM.from_pretrained(
         repo,
         return_dict=True,

 language:
 - ko
 datasets:
+- kyujinpy/OpenOrca-ko-v3
 library_name: transformers
 pipeline_tag: text-generation
 license: cc-by-nc-sa-4.0
 **Base Model**  [hyunseoki/ko-en-llama2-13b](https://huggingface.co/hyunseoki/ko-en-llama2-13b)
 **Training Dataset**
+I use [OpenOrca-ko-v3](https://huggingface.co/datasets/kyujinpy/OpenOrca-ko-v3).
 Using DeepL, translate about [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).
 I use A100 GPU 40GB and COLAB, when trianing.
 | Model | Average |Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
 | --- | --- | --- | --- | --- | --- | --- |
 | [Korean-OpenOrca-13B🐳] | 48.79 | 43.09 | 54.13 | 40.24 | 45.22 | 61.28 |
+| [Korean-OpenOrca-13B-v2🐳] | 48.17 | 43.17 | 54.51 | 42.90 | 41.82 | 58.44 |
+| Korean-OpenOrca-13B-v3🐳 | 48.86 | 43.77 | 54.30 | 41.79 | 43.85 | 60.57 |
 # Implementation Code
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+repo = "kyujinpy/Korean-OpenOrca-13B-v3"
 OpenOrca = AutoModelForCausalLM.from_pretrained(
         repo,
         return_dict=True,