Instructions to use h2oai/h2o-danube2-1.8b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h2oai/h2o-danube2-1.8b-chat with Transformers:

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

pipe = pipeline("text-generation", model="h2oai/h2o-danube2-1.8b-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h2oai/h2o-danube2-1.8b-chat")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2o-danube2-1.8b-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use h2oai/h2o-danube2-1.8b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h2oai/h2o-danube2-1.8b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h2oai/h2o-danube2-1.8b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/h2oai/h2o-danube2-1.8b-chat

SGLang

How to use h2oai/h2o-danube2-1.8b-chat 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 "h2oai/h2o-danube2-1.8b-chat" \
    --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": "h2oai/h2o-danube2-1.8b-chat",
		"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 "h2oai/h2o-danube2-1.8b-chat" \
        --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": "h2oai/h2o-danube2-1.8b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use h2oai/h2o-danube2-1.8b-chat with Docker Model Runner:
```
docker model run hf.co/h2oai/h2o-danube2-1.8b-chat
```

Chat template?

by BoscoTheDog - opened Apr 20, 2024

Discussion

BoscoTheDog

Apr 20, 2024

Just to be sure: does this model use the Mistral chat template? The model card doesn't mention it, but does imply it.

i.e. im_start_im_end

ilu000

H2O.ai org Apr 22, 2024

The model uses a custom chat template, which is described in the tokenizer_config.json (https://huggingface.co/h2oai/h2o-danube2-1.8b-chat/blob/main/tokenizer_config.json#L33). This is automatically picked when using the transformers pipeline.

For more information about chat templates, visit https://huggingface.co/docs/transformers/main/en/chat_templating

psinger

Apr 22, 2024

Added an example to the model card: <|prompt|>Why is drinking water so healthy?</s><|answer|>

psinger changed discussion status to closed Apr 22, 2024

BoscoTheDog

Apr 23, 2024

•

edited Apr 23, 2024

Thanks, now I know where to look for that stuff!

Unfortunately I can't use the transformers pipeline to manage this, since I'm trying to incorporate Danube in a 100% browser-based project. So I have to build the templating engine myself. That's why a clear example of what a finished template should look like would be so helpful.

For example, see https://github.com/ngxson/wllama

BoscoTheDog

Apr 23, 2024

Whoa, psinger read my mind :-) Thanks!

Is it all on one line? So even if there are multiple questions and answers in remains on one line?

psinger

Apr 23, 2024

yeah one line:

etc

BoscoTheDog

Apr 26, 2024

My compliments on the model by the way. Now that the prompt is working it's doing really wel for it's size (Q5), and has become a favourite for me. I hope you will make a version with an even bigger context.

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