Instructions to use Markr-AI/COKAL-DPO-13b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Markr-AI/COKAL-DPO-13b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Markr-AI/COKAL-DPO-13b-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Markr-AI/COKAL-DPO-13b-v2")
model = AutoModelForCausalLM.from_pretrained("Markr-AI/COKAL-DPO-13b-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Markr-AI/COKAL-DPO-13b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Markr-AI/COKAL-DPO-13b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Markr-AI/COKAL-DPO-13b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Markr-AI/COKAL-DPO-13b-v2

SGLang

How to use Markr-AI/COKAL-DPO-13b-v2 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 "Markr-AI/COKAL-DPO-13b-v2" \
    --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": "Markr-AI/COKAL-DPO-13b-v2",
		"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 "Markr-AI/COKAL-DPO-13b-v2" \
        --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": "Markr-AI/COKAL-DPO-13b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Markr-AI/COKAL-DPO-13b-v2 with Docker Model Runner:
```
docker model run hf.co/Markr-AI/COKAL-DPO-13b-v2
```

DopeorNope commited on Jan 16, 2024

Commit

9d2939f

verified ·

1 Parent(s): 9d05c14

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -11,9 +11,6 @@ license: cc-by-nc-sa-4.0
 **(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄으로 개발된 모델입니다**
-**DopeorNope개발자가 훈련하여 업로드한 모델입니다**
-**개발의 권한은 DopeorNope(Seungyoo Lee)에게 있으며, 모델 문의사항은 컨택 바랍니다**
 **The license is `cc-by-nc-sa-4.0`.**
@@ -85,9 +82,9 @@ model_tokenizer = AutoTokenizer.from_pretrained(repo)
 # Acknowledgement
-이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
-This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.

 **(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄으로 개발된 모델입니다**
 **The license is `cc-by-nc-sa-4.0`.**
 # Acknowledgement
+- 이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 '인공지능 중심 산업융합 집적단지 조성사업'으로 지원을 받아 수행된 연구 결과입니다.
+- This model was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea)&Gwangju Metropolitan City.