Instructions to use Nexusflow/NexusRaven-V2-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexusflow/NexusRaven-V2-13B with Transformers:

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

pipe = pipeline("text-generation", model="Nexusflow/NexusRaven-V2-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Nexusflow/NexusRaven-V2-13B")
model = AutoModelForMultimodalLM.from_pretrained("Nexusflow/NexusRaven-V2-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nexusflow/NexusRaven-V2-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nexusflow/NexusRaven-V2-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexusflow/NexusRaven-V2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Nexusflow/NexusRaven-V2-13B

SGLang

How to use Nexusflow/NexusRaven-V2-13B 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 "Nexusflow/NexusRaven-V2-13B" \
    --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": "Nexusflow/NexusRaven-V2-13B",
		"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 "Nexusflow/NexusRaven-V2-13B" \
        --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": "Nexusflow/NexusRaven-V2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nexusflow/NexusRaven-V2-13B with Docker Model Runner:
```
docker model run hf.co/Nexusflow/NexusRaven-V2-13B
```

Never generates <bot_end>

#14

by kjhamilton - opened Jan 2, 2024

Discussion

kjhamilton

Jan 2, 2024

•

edited Jan 2, 2024

Sending calls locally I see:

"choices": [
    {
      "index": 0,
      "text": " \nCall: get_current_weather(location=getlatlong(location='San Francisco')) \nThought: The function call `get_current_weather(location=getlatlong(location='San Francisco'))` answers the question because

... on and on...

It never generates bot_end - instead if I set the stop to "Thought: " - then it does stop.

kjhamilton

Jan 2, 2024

I see in the code that this may be due to the server not retaining special tokens. Thanks!

kjhamilton changed discussion status to closed Jan 17, 2024

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