Instructions to use TeeA/DEPLOT-ViChart-word with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeA/DEPLOT-ViChart-word with Transformers:

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

pipe = pipeline("image-text-to-text", model="TeeA/DEPLOT-ViChart-word")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("TeeA/DEPLOT-ViChart-word")
model = AutoModelForMultimodalLM.from_pretrained("TeeA/DEPLOT-ViChart-word", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TeeA/DEPLOT-ViChart-word with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TeeA/DEPLOT-ViChart-word

SGLang

How to use TeeA/DEPLOT-ViChart-word 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 "TeeA/DEPLOT-ViChart-word" \
    --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": "TeeA/DEPLOT-ViChart-word",
		"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 "TeeA/DEPLOT-ViChart-word" \
        --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": "TeeA/DEPLOT-ViChart-word",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TeeA/DEPLOT-ViChart-word with Docker Model Runner:
```
docker model run hf.co/TeeA/DEPLOT-ViChart-word
```

TeeA commited on Jan 16, 2024

Commit

0330833

verified ·

1 Parent(s): e992f28

Upload Pix2StructForConditionalGeneration

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -15,7 +15,7 @@
     "encoder_hidden_size": 768,
     "initializer_range": 0.02,
     "model_type": "pix2struct_text_model",
-    "vocab_size": 70215
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

     "encoder_hidden_size": 768,
     "initializer_range": 0.02,
     "model_type": "pix2struct_text_model",
+    "vocab_size": 36098
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7915748488c96a451883cd3626083a04a66204fa1893594a12ef5f4fabdf9371
-size 1251879880

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b692ffd9cfcba79d98ecc11e50f3e2df30c8fef5435ccf7538d17b1e65ad4db
+size 1042264896