Instructions to use pavan-visionet/dummy_docvqa_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pavan-visionet/dummy_docvqa_v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="pavan-visionet/dummy_docvqa_v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("pavan-visionet/dummy_docvqa_v1")
model = AutoModelForMultimodalLM.from_pretrained("pavan-visionet/dummy_docvqa_v1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pavan-visionet/dummy_docvqa_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pavan-visionet/dummy_docvqa_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pavan-visionet/dummy_docvqa_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pavan-visionet/dummy_docvqa_v1

SGLang

How to use pavan-visionet/dummy_docvqa_v1 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 "pavan-visionet/dummy_docvqa_v1" \
    --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": "pavan-visionet/dummy_docvqa_v1",
		"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 "pavan-visionet/dummy_docvqa_v1" \
        --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": "pavan-visionet/dummy_docvqa_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pavan-visionet/dummy_docvqa_v1 with Docker Model Runner:
```
docker model run hf.co/pavan-visionet/dummy_docvqa_v1
```

pavan-visionet commited on Aug 24, 2023

Commit

dca8bdf

1 Parent(s): fe6d98b

max_lenght=50

Browse files

Files changed (2) hide show

preprocessor_config.json +2 -2
tokenizer.json +2 -2

preprocessor_config.json CHANGED Viewed

@@ -20,7 +20,7 @@
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": [
-    640,
-    960
   ]
 }

   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": [
+    720,
+    1280
   ]
 }

tokenizer.json CHANGED Viewed

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

   "version": "1.0",
   "truncation": {
     "direction": "Right",
+    "max_length": 50,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
+      "Fixed": 50
     },
     "direction": "Right",
     "pad_to_multiple_of": null,