Instructions to use WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="WhiteRabbitNeo/WhiteRabbitNeo-13B-v1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-13B-v1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-13B-v1", trust_remote_code=True)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/WhiteRabbitNeo/WhiteRabbitNeo-13B-v1

SGLang

How to use WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 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 "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1" \
    --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": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1",
		"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 "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1" \
        --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": "WhiteRabbitNeo/WhiteRabbitNeo-13B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 with Docker Model Runner:
```
docker model run hf.co/WhiteRabbitNeo/WhiteRabbitNeo-13B-v1
```

Problem with configuring offload_folder

#12

by ManneDK - opened Feb 23, 2024

Discussion

ManneDK

Feb 23, 2024

I have a problem, maybe someone can help me:
ValueError: The current device_map had weights offloaded to the disk. Please provide an offload_folder for them. Alternatively, make
sure you have safetensors installed if the model you are using offers the weights in this format.

I have safetensors installed:
(base) manne@ManneMint:~/AI/text-generation-webui$ pip show safetensors
Name: safetensors
Version: 0.4.2
Summary:
Home-page:
Author:
Author-email: Nicolas Patry patry.nicolas@protonmail.com
License:
Location: /home/manne/.local/lib/python3.10/site-packages
Requires:
Required-by: timm, transformers

How do i set an offload_folder? i have tryed:
offload_folder = "~/AI/text-generation-webui/offload",
And it doesn't work for me, anyone there can help?

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