Instructions to use NaughtyDog97/DFE-GPS-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NaughtyDog97/DFE-GPS-9B with Transformers:

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

pipe = pipeline("text-generation", model="NaughtyDog97/DFE-GPS-9B", 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/DFE-GPS-9B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NaughtyDog97/DFE-GPS-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NaughtyDog97/DFE-GPS-9B"
# 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/DFE-GPS-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NaughtyDog97/DFE-GPS-9B

SGLang

How to use NaughtyDog97/DFE-GPS-9B 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/DFE-GPS-9B" \
    --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/DFE-GPS-9B",
		"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/DFE-GPS-9B" \
        --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/DFE-GPS-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NaughtyDog97/DFE-GPS-9B with Docker Model Runner:
```
docker model run hf.co/NaughtyDog97/DFE-GPS-9B
```

zezeze97 commited on Aug 28, 2024

Commit

97ecdbf

1 Parent(s): b92e464

111

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -4,7 +4,7 @@ license: apache-2.0
 # Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver
 ## Model Structure
-<img src="sample/DFE-GPS.png" alt="Alt text" width="30%" height="auto">
 - **Diagram Encoder**: [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
@@ -18,7 +18,7 @@ Before running the script, install the following necessary dependencies.
 pip install torch transformers==4.40.0 accelerate pillow sentencepiece
 ```
-You can solve geometric problems using the following script. First, formalize the geometric images with the Diagram Formalizer, and then use the multi-modal reasing model for problem-solving:
 ```python
 import torch
@@ -65,7 +65,6 @@ def parse_cdl(input_string):
         if match:
             results[key] = match.group(1).strip()
         else:
-            # 如果未找到包含"calibrate"的版本，尝试匹配不含"calibrate"的版本
             pattern = pattern.replace("(?:calibrate )", "(?:calibrate )?")
             match = re.search(pattern, input_string, re.DOTALL)
             if match:

 # Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver
 ## Model Structure
+<img src="sample/DFE-GPS.png" alt="Alt text" width="80%" height="auto">
 - **Diagram Encoder**: [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
 pip install torch transformers==4.40.0 accelerate pillow sentencepiece
 ```
+You can solve geometric problems using the following script. First, formalize the geometric images with the [Diagram Formalizer](https://huggingface.co/NaughtyDog97/DiagramFormalizer), and then use the multi-modal reasing model for problem-solving:
 ```python
 import torch
         if match:
             results[key] = match.group(1).strip()
         else:
             pattern = pattern.replace("(?:calibrate )", "(?:calibrate )?")
             match = re.search(pattern, input_string, re.DOTALL)
             if match: