Instructions to use Open-Orca/LlongOrca-13B-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Open-Orca/LlongOrca-13B-16k with Transformers:

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

pipe = pipeline("text-generation", model="Open-Orca/LlongOrca-13B-16k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Open-Orca/LlongOrca-13B-16k")
model = AutoModelForCausalLM.from_pretrained("Open-Orca/LlongOrca-13B-16k")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Open-Orca/LlongOrca-13B-16k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Open-Orca/LlongOrca-13B-16k"
# 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/LlongOrca-13B-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Open-Orca/LlongOrca-13B-16k

SGLang

How to use Open-Orca/LlongOrca-13B-16k 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/LlongOrca-13B-16k" \
    --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/LlongOrca-13B-16k",
		"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/LlongOrca-13B-16k" \
        --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/LlongOrca-13B-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Open-Orca/LlongOrca-13B-16k with Docker Model Runner:
```
docker model run hf.co/Open-Orca/LlongOrca-13B-16k
```

Severe repetition when input length is longer than 7k token

by zefanwang - opened Sep 9, 2023

Discussion

zefanwang

Sep 9, 2023

Hi, I really appreciate the work. I am taking an inference with LlongOrca-13B-16k( with extremely low temperature and top_p) on long text. However, I've noticed severe repetition on the output.
I'm curious to know if the finetuning data from the Orca dataset was concatenated to long samples. If not, this behavior might be expected.
Additionally, it would be greatly appreciated if more insights into the training process could be provided.

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