Instructions to use Open-Orca/OpenOrca-Platypus2-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Open-Orca/OpenOrca-Platypus2-13B with Transformers:

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

pipe = pipeline("text-generation", model="Open-Orca/OpenOrca-Platypus2-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Open-Orca/OpenOrca-Platypus2-13B")
model = AutoModelForCausalLM.from_pretrained("Open-Orca/OpenOrca-Platypus2-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Open-Orca/OpenOrca-Platypus2-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Open-Orca/OpenOrca-Platypus2-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Open-Orca/OpenOrca-Platypus2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Open-Orca/OpenOrca-Platypus2-13B

SGLang

How to use Open-Orca/OpenOrca-Platypus2-13B 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 "Open-Orca/OpenOrca-Platypus2-13B" \
    --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": "Open-Orca/OpenOrca-Platypus2-13B",
		"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 "Open-Orca/OpenOrca-Platypus2-13B" \
        --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": "Open-Orca/OpenOrca-Platypus2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Open-Orca/OpenOrca-Platypus2-13B with Docker Model Runner:
```
docker model run hf.co/Open-Orca/OpenOrca-Platypus2-13B
```

Inconsistency with end of string token

by cvdbdo - opened Aug 17, 2023

Discussion

cvdbdo

Aug 17, 2023

When generating text I get either or <|end_of_turn|> as EOS token. With <|end_of_turn|> the generation doesn't stop.

bleysg

OpenOrca org Aug 17, 2023

Can you provide more details on the execution environment? Which prompt format are you using? We’ve only tested with the one from OpenOrca model.

cvdbdo changed discussion title from Inconsistency with end of strins token to Inconsistency with end of string token Aug 17, 2023

cvdbdo

Aug 17, 2023

•

edited Sep 11, 2023

I use Alpaca Instruct format, with a Open-Orca/OpenOrca-Platypus2-13B fine tuned on a specialized instruct dataset. The behaviour described is common to the base and fine tuned models. It happens with or without quantization (4 & 8 bits). I load them with a simple AutoModelForCausalLM.

generation_config = GenerationConfig(
temperature=.0001,
top_p=0,
top_k=0,
repetition_penalty=1,
)

The problem is mainly a performance one because the model keeps generating after the eos token.

darshan12

Sep 7, 2023

•

edited Sep 7, 2023

How to fine tune this model can anyone please connect with me and help me, I want to learn how to fine tune this data?
Email: darshankholakiya12@gmail.com
LinkedIn: https://www.linkedin.com/in/darshankholakiya/

deleted

Sep 12, 2023

•

edited Sep 12, 2023

I use Alpaca Instruct format, with a Open-Orca/OpenOrca-Platypus2-13B fine tuned on a specialized instruct dataset. The behaviour described is common to the base and fine tuned models. It happens with or without quantization (4 & 8 bits). I load them with a simple AutoModelForCausalLM.

generation_config = GenerationConfig(
temperature=.0001,
top_p=0,
top_k=0,
repetition_penalty=1,
)

The problem is mainly a performance one because the model keeps generating after the eos token.

Set the end to turn token as stop token in GenerationConfig. If you don't know the token id then simple encode the <|end_of_turn|> using the tokenizer you will get the id then set stop token to this id.

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