Instructions to use Xenova/tiny-random-Florence2ForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xenova/tiny-random-Florence2ForConditionalGeneration with Transformers:

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

pipe = pipeline("image-text-to-text", model="Xenova/tiny-random-Florence2ForConditionalGeneration", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Xenova/tiny-random-Florence2ForConditionalGeneration", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("Xenova/tiny-random-Florence2ForConditionalGeneration", trust_remote_code=True)

Transformers.js

How to use Xenova/tiny-random-Florence2ForConditionalGeneration with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('image-text-to-text', 'Xenova/tiny-random-Florence2ForConditionalGeneration');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xenova/tiny-random-Florence2ForConditionalGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xenova/tiny-random-Florence2ForConditionalGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xenova/tiny-random-Florence2ForConditionalGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Xenova/tiny-random-Florence2ForConditionalGeneration

SGLang

How to use Xenova/tiny-random-Florence2ForConditionalGeneration 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 "Xenova/tiny-random-Florence2ForConditionalGeneration" \
    --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": "Xenova/tiny-random-Florence2ForConditionalGeneration",
		"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 "Xenova/tiny-random-Florence2ForConditionalGeneration" \
        --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": "Xenova/tiny-random-Florence2ForConditionalGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xenova/tiny-random-Florence2ForConditionalGeneration with Docker Model Runner:
```
docker model run hf.co/Xenova/tiny-random-Florence2ForConditionalGeneration
```

Xenova HF Staff commited on Jun 21, 2024

Commit

5436b64

verified ·

1 Parent(s): 3fe86b7

Update preprocessor_config.json

Browse files

Files changed (1) hide show

preprocessor_config.json +37 -1

preprocessor_config.json CHANGED Viewed

@@ -17,7 +17,7 @@
     "input_data_format"
   ],
   "auto_map": {
-    "AutoProcessor": "microsoft/Florence-2-base-ft--processing_florence2.Florence2Processor"
   },
   "crop_size": {
     "height": 768,
@@ -46,5 +46,41 @@
   "size": {
     "height": 768,
     "width": 768
   }
 }

     "input_data_format"
   ],
   "auto_map": {
+    "AutoProcessor": "processing_florence2.Florence2Processor"
   },
   "crop_size": {
     "height": 768,
   "size": {
     "height": 768,
     "width": 768
+  },
+  "tasks_answer_post_processing_type": {
+    "<OCR>": "pure_text",
+    "<OCR_WITH_REGION>": "ocr",
+    "<CAPTION>": "pure_text",
+    "<DETAILED_CAPTION>": "pure_text",
+    "<MORE_DETAILED_CAPTION>": "pure_text",
+    "<OD>": "description_with_bboxes",
+    "<DENSE_REGION_CAPTION>": "description_with_bboxes",
+    "<CAPTION_TO_PHRASE_GROUNDING>": "phrase_grounding",
+    "<REFERRING_EXPRESSION_SEGMENTATION>": "polygons",
+    "<REGION_TO_SEGMENTATION>": "polygons",
+    "<OPEN_VOCABULARY_DETECTION>": "description_with_bboxes_or_polygons",
+    "<REGION_TO_CATEGORY>": "pure_text",
+    "<REGION_TO_DESCRIPTION>": "pure_text",
+    "<REGION_TO_OCR>": "pure_text",
+    "<REGION_PROPOSAL>": "bboxes"
+  },
+  "task_prompts_without_inputs": {
+    "<OCR>": "What is the text in the image?",
+    "<OCR_WITH_REGION>": "What is the text in the image, with regions?",
+    "<CAPTION>": "What does the image describe?",
+    "<DETAILED_CAPTION>": "Describe in detail what is shown in the image.",
+    "<MORE_DETAILED_CAPTION>": "Describe with a paragraph what is shown in the image.",
+    "<OD>": "Locate the objects with category name in the image.",
+    "<DENSE_REGION_CAPTION>": "Locate the objects in the image, with their descriptions.",
+    "<REGION_PROPOSAL>": "Locate the region proposals in the image."
+  },
+  "task_prompts_with_input": {
+    "<CAPTION_TO_PHRASE_GROUNDING>": "Locate the phrases in the caption: {input}",
+    "<REFERRING_EXPRESSION_SEGMENTATION>": "Locate {input} in the image with mask",
+    "<REGION_TO_SEGMENTATION>": "What is the polygon mask of region {input}",
+    "<OPEN_VOCABULARY_DETECTION>": "Locate {input} in the image.",
+    "<REGION_TO_CATEGORY>": "What is the region {input}?",
+    "<REGION_TO_DESCRIPTION>": "What does the region {input} describe?",
+    "<REGION_TO_OCR>": "What text is in the region {input}?",
   }
 }