Instructions to use NaughtyDog97/DiagramFormalizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NaughtyDog97/DiagramFormalizer with Transformers:

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

pipe = pipeline("text-generation", model="NaughtyDog97/DiagramFormalizer", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NaughtyDog97/DiagramFormalizer", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NaughtyDog97/DiagramFormalizer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NaughtyDog97/DiagramFormalizer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NaughtyDog97/DiagramFormalizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NaughtyDog97/DiagramFormalizer

SGLang

How to use NaughtyDog97/DiagramFormalizer 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 "NaughtyDog97/DiagramFormalizer" \
    --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": "NaughtyDog97/DiagramFormalizer",
		"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 "NaughtyDog97/DiagramFormalizer" \
        --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": "NaughtyDog97/DiagramFormalizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NaughtyDog97/DiagramFormalizer with Docker Model Runner:
```
docker model run hf.co/NaughtyDog97/DiagramFormalizer
```

zezeze97 commited on Aug 28, 2024

Commit

cd4ed1d

1 Parent(s): d537287

123

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -4,7 +4,7 @@ license: apache-2.0
 # Diagram Formalizer
 Model Structure:
-<img src="sample/diagram_formalizer.png" alt="Alt text" width="80%" height="auto">
 - **Diagram Encoder**: [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
@@ -47,7 +47,7 @@ tokenizer = AutoTokenizer.from_pretrained(
 # text prompt
 img_path = 'sample/4927.png'
 prompt = 'Based on the image, first describe what you see in the figure, then predict the construction_cdl and image_cdl and calibrate it.'
-text = f"<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
 def tokenizer_image_token(prompt, tokenizer, image_token_index, return_tensors=None):
     prompt_chunks = [tokenizer(chunk).input_ids for chunk in prompt.split('<image>')]

 # Diagram Formalizer
 Model Structure:
+<img src="sample/diagram_formalizer.png" alt="Alt text" width="50%" height="auto">
 - **Diagram Encoder**: [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
 # text prompt
 img_path = 'sample/4927.png'
 prompt = 'Based on the image, first describe what you see in the figure, then predict the construction_cdl and image_cdl and calibrate it.'
+text = f'<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\n{prompt}<|im_end|>\n<|im_start|>assistant\n'
 def tokenizer_image_token(prompt, tokenizer, image_token_index, return_tensors=None):
     prompt_chunks = [tokenizer(chunk).input_ids for chunk in prompt.split('<image>')]