Instructions to use WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a with Transformers:

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

pipe = pipeline("text-generation", model="WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a")
model = AutoModelForCausalLM.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a"
# 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-7B-v1.5a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a

SGLang

How to use WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a 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-7B-v1.5a" \
    --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-7B-v1.5a",
		"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-7B-v1.5a" \
        --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-7B-v1.5a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a with Docker Model Runner:
```
docker model run hf.co/WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a
```

Appropriate chat template

by hannahbernstein - opened Feb 29, 2024

Discussion

hannahbernstein

Feb 29, 2024

Is llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: " the most optimal template for chatting? Because there's no chat template in the tokenizer_config.json file, grabbing the tokenizer and applying the chat defaults to the LlamaTokenizer class. Could you add a chat template to this model?

I'm also seeing sequences like <|User|>, <|Assistant|>, <｜begin▁of▁sentence｜>, <｜end▁of▁sentence｜>, etc. If these are part of the model's vocabulary, what is the most optimal prompting?

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