Instructions to use NousResearch/Nous-Hermes-2-Vision-Alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Nous-Hermes-2-Vision-Alpha with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Nous-Hermes-2-Vision-Alpha")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-2-Vision-Alpha", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Nous-Hermes-2-Vision-Alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Nous-Hermes-2-Vision-Alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Nous-Hermes-2-Vision-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NousResearch/Nous-Hermes-2-Vision-Alpha

SGLang

How to use NousResearch/Nous-Hermes-2-Vision-Alpha 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 "NousResearch/Nous-Hermes-2-Vision-Alpha" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Nous-Hermes-2-Vision-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "NousResearch/Nous-Hermes-2-Vision-Alpha" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Nous-Hermes-2-Vision-Alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NousResearch/Nous-Hermes-2-Vision-Alpha with Docker Model Runner:
```
docker model run hf.co/NousResearch/Nous-Hermes-2-Vision-Alpha
```

KeyError llava_mistral

by janrudolf - opened Dec 7, 2023

Discussion

janrudolf

Dec 7, 2023

•

edited Dec 7, 2023

Hi,

when I try to run the code

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-2-Vision-Alpha")

I have the error KeyError: 'llava_mistral'. Do you know how to resolve it?

Moghrua

Dec 8, 2023

Seeing the same error. Looks like the model file is split into two parts - maybe the automatic pipeline is missing a key step? Wild guess!

snimu

Feb 6, 2024

The same happens with BakLLaVA-1: https://huggingface.co/SkunkworksAI/BakLLaVA-1
Seems to be a general issue with transformers + LLaVA

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