Instructions to use Pengyu965/ChartReformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pengyu965/ChartReformer with Transformers:

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

pipe = pipeline("image-text-to-text", model="Pengyu965/ChartReformer")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Pengyu965/ChartReformer")
model = AutoModelForMultimodalLM.from_pretrained("Pengyu965/ChartReformer", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pengyu965/ChartReformer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pengyu965/ChartReformer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pengyu965/ChartReformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Pengyu965/ChartReformer

SGLang

How to use Pengyu965/ChartReformer 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 "Pengyu965/ChartReformer" \
    --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": "Pengyu965/ChartReformer",
		"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 "Pengyu965/ChartReformer" \
        --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": "Pengyu965/ChartReformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Pengyu965/ChartReformer with Docker Model Runner:
```
docker model run hf.co/Pengyu965/ChartReformer
```

ChartReformer / train_state.json

Pengyu965

Upload ChartReformer checkpoints (ICDAR 2024) and model card

e7062e9 verified 17 days ago

Raw History Blame Contribute Delete

509 Bytes

{
  "run_name": "finetune_new_edits_data",
  "max_length": 1024,
  "per_device_train_batch_size": 4,
  "per_device_eval_batch_size": 4,
  "gradient_accumulation_steps": 1,
  "learning_rate": 2e-05,
  "weight_decay": 1e-05,
  "num_warmup_steps": 500,
  "train_batch_size": 16,
  "num_train_epochs": 20,
  "max_steps": 387000,
  "checkpointing_steps": "5000",
  "epoch": 1,
  "global_step": 20000,
  "train_loss": 0.03977988660335541,
  "eval_loss": 0.05922633409500122,
  "current_lr": 1.9874737996766403e-05
}

	{
	"run_name": "finetune_new_edits_data",
	"max_length": 1024,
	"per_device_train_batch_size": 4,
	"per_device_eval_batch_size": 4,
	"gradient_accumulation_steps": 1,
	"learning_rate": 2e-05,
	"weight_decay": 1e-05,
	"num_warmup_steps": 500,
	"train_batch_size": 16,
	"num_train_epochs": 20,
	"max_steps": 387000,
	"checkpointing_steps": "5000",
	"epoch": 1,
	"global_step": 20000,
	"train_loss": 0.03977988660335541,
	"eval_loss": 0.05922633409500122,
	"current_lr": 1.9874737996766403e-05
	}