Text Generation
Transformers
Safetensors
DIVEdoc
docvqa
distillation
VLM
document-understanding
OCR-free
custom_code
Instructions to use JayRay5/DIVE-Doc-FRD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JayRay5/DIVE-Doc-FRD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JayRay5/DIVE-Doc-FRD", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("JayRay5/DIVE-Doc-FRD", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use JayRay5/DIVE-Doc-FRD with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JayRay5/DIVE-Doc-FRD" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JayRay5/DIVE-Doc-FRD", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JayRay5/DIVE-Doc-FRD
- SGLang
How to use JayRay5/DIVE-Doc-FRD 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 "JayRay5/DIVE-Doc-FRD" \ --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": "JayRay5/DIVE-Doc-FRD", "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 "JayRay5/DIVE-Doc-FRD" \ --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": "JayRay5/DIVE-Doc-FRD", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JayRay5/DIVE-Doc-FRD with Docker Model Runner:
docker model run hf.co/JayRay5/DIVE-Doc-FRD
Update modeling_divedoc.py
Browse files- modeling_divedoc.py +1 -1
modeling_divedoc.py
CHANGED
|
@@ -22,7 +22,7 @@ from transformers.models.donut.modeling_donut_swin import DonutSwinModel
|
|
| 22 |
|
| 23 |
|
| 24 |
from .config_divedoc import SwinPamVisionEncoderConfig, SiglipPAMVisionEncoderConfig, DIVEdocConfig
|
| 25 |
-
from typing import List, Optional, Tuple, Union
|
| 26 |
from dataclasses import dataclass
|
| 27 |
|
| 28 |
|
|
|
|
| 22 |
|
| 23 |
|
| 24 |
from .config_divedoc import SwinPamVisionEncoderConfig, SiglipPAMVisionEncoderConfig, DIVEdocConfig
|
| 25 |
+
from typing import List, Optional, Tuple, Union, Literal
|
| 26 |
from dataclasses import dataclass
|
| 27 |
|
| 28 |
|