Instructions to use ermu2001/pllava-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ermu2001/pllava-34b with Transformers:

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

pipe = pipeline("text-generation", model="ermu2001/pllava-34b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("ermu2001/pllava-34b")
model = AutoModelForSeq2SeqLM.from_pretrained("ermu2001/pllava-34b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ermu2001/pllava-34b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ermu2001/pllava-34b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ermu2001/pllava-34b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ermu2001/pllava-34b

SGLang

How to use ermu2001/pllava-34b 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 "ermu2001/pllava-34b" \
    --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": "ermu2001/pllava-34b",
		"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 "ermu2001/pllava-34b" \
        --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": "ermu2001/pllava-34b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ermu2001/pllava-34b with Docker Model Runner:
```
docker model run hf.co/ermu2001/pllava-34b
```

Host the demo on Hugging Face Spaces instead

by merve - opened Apr 30, 2024

Discussion

merve

Apr 30, 2024

Hello hello! Congrats for the release! 🎉

I saw you host your demo somewhere else although built with gradio, if you'd like to carry it to Hugging Face Spaces we can provide hardware grant. WDYT?

ermu2001

Owner Apr 30, 2024

Fantastic!!!

We're trying to set up a space for 13b here: https://huggingface.co/spaces/DiscloseAI/pllava-13b-demo . And next we'll set up one for 34B model.

Still struggling with the environment😭

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