Instructions to use ssh1419/indi-deplot-batch-16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ssh1419/indi-deplot-batch-16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ssh1419/indi-deplot-batch-16")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ssh1419/indi-deplot-batch-16")
model = AutoModelForMultimodalLM.from_pretrained("ssh1419/indi-deplot-batch-16")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ssh1419/indi-deplot-batch-16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ssh1419/indi-deplot-batch-16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ssh1419/indi-deplot-batch-16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ssh1419/indi-deplot-batch-16

SGLang

How to use ssh1419/indi-deplot-batch-16 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 "ssh1419/indi-deplot-batch-16" \
    --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": "ssh1419/indi-deplot-batch-16",
		"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 "ssh1419/indi-deplot-batch-16" \
        --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": "ssh1419/indi-deplot-batch-16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ssh1419/indi-deplot-batch-16 with Docker Model Runner:
```
docker model run hf.co/ssh1419/indi-deplot-batch-16
```

ssh1419 commited on Aug 29, 2024

Commit

5ffc446

verified ·

1 Parent(s): 3dbf5ff

Upload processor

Browse files

Files changed (1) hide show

tokenizer_config.json +4 -0

tokenizer_config.json CHANGED Viewed

@@ -930,8 +930,12 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "Pix2StructProcessor",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",

   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "max_length": 1000,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "processor_class": "Pix2StructProcessor",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",