Instructions to use OEvortex/HelpingAI-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OEvortex/HelpingAI-Vision with Transformers:

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

pipe = pipeline("image-text-to-text", model="OEvortex/HelpingAI-Vision", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OEvortex/HelpingAI-Vision", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OEvortex/HelpingAI-Vision with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OEvortex/HelpingAI-Vision

SGLang

How to use OEvortex/HelpingAI-Vision 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 "OEvortex/HelpingAI-Vision" \
    --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": "OEvortex/HelpingAI-Vision",
		"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 "OEvortex/HelpingAI-Vision" \
        --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": "OEvortex/HelpingAI-Vision",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OEvortex/HelpingAI-Vision with Docker Model Runner:
```
docker model run hf.co/OEvortex/HelpingAI-Vision
```

Abhaykoul commited on Jan 19, 2024

Commit

51a6725

verified ·

1 Parent(s): 983f690

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -31

README.md CHANGED Viewed

@@ -58,11 +58,11 @@ You are Dolphin, a helpful AI assistant.<|im_end|>
 ```python
 from huggingface_hub import hf_hub_download
-hf_hub_download(repo_id="visheratin/LLaVA-3b", filename="configuration_llava.py", local_dir="./", force_download=True)
-hf_hub_download(repo_id="visheratin/LLaVA-3b", filename="configuration_phi.py", local_dir="./", force_download=True)
-hf_hub_download(repo_id="visheratin/LLaVA-3b", filename="modeling_llava.py", local_dir="./", force_download=True)
-hf_hub_download(repo_id="visheratin/LLaVA-3b", filename="modeling_phi.py", local_dir="./", force_download=True)
-hf_hub_download(repo_id="visheratin/LLaVA-3b", filename="processing_llava.py", local_dir="./", force_download=True)
 ```
 **Create a model**
@@ -71,7 +71,7 @@ hf_hub_download(repo_id="visheratin/LLaVA-3b", filename="processing_llava.py", l
 from modeling_llava import LlavaForConditionalGeneration
 import torch
-model = LlavaForConditionalGeneration.from_pretrained("visheratin/LLaVA-3b", torch_dtype=torch.float16)
 model = model.to("cuda")
 ```
@@ -81,7 +81,7 @@ model = model.to("cuda")
 from transformers import AutoTokenizer
 from processing_llava import LlavaProcessor, OpenCLIPImageProcessor
-tokenizer = AutoTokenizer.from_pretrained("visheratin/LLaVA-3b")
 image_processor = OpenCLIPImageProcessor(model.config.preprocess_config)
 processor = LlavaProcessor(image_processor, tokenizer)
 ```
@@ -123,27 +123,3 @@ import torch
 with torch.inference_mode():
   output = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.4, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id)
 ```
-## Benchmarks
-- TextVQA - 38.59%
-- GQA - 49.6%
-- VQAv2 - 64.24%
-- VizWiz - 24.88%
-- POPE - 80.59%
-- V*-bench - 52.25% (OCR - 46.66%, GPT4V-hard - 41.17%, direct attributes - 43.48%, relative position - 65.79%)
-## Examples
-<a target="_blank" href="https://colab.research.google.com/drive/1sXDvVl5s9fTcE0N2bQGOlXhnNlKEdeun">
-  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
-</a>
-## License
-The model is licensed under MIT license, but since the data used for model training is largely synthetic, you should also follow OpenAI and Google Gemini terms of service.
-Which means don't create competitor models for them.
-## Acknowledgments
-Thanks to [ML Collective](https://mlcollective.org/) for providing credits for computing resources.

 ```python
 from huggingface_hub import hf_hub_download
+hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="configuration_llava.py", local_dir="./", force_download=True)
+hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="configuration_phi.py", local_dir="./", force_download=True)
+hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="modeling_llava.py", local_dir="./", force_download=True)
+hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="modeling_phi.py", local_dir="./", force_download=True)
+hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="processing_llava.py", local_dir="./", force_download=True)
 ```
 **Create a model**
 from modeling_llava import LlavaForConditionalGeneration
 import torch
+model = LlavaForConditionalGeneration.from_pretrained("OEvortex/HelpingAI-Vision", torch_dtype=torch.float16)
 model = model.to("cuda")
 ```
 from transformers import AutoTokenizer
 from processing_llava import LlavaProcessor, OpenCLIPImageProcessor
+tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-Vision")
 image_processor = OpenCLIPImageProcessor(model.config.preprocess_config)
 processor = LlavaProcessor(image_processor, tokenizer)
 ```
 with torch.inference_mode():
   output = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.4, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id)
 ```