Instructions to use arvisioncode/florence_custom_uom1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arvisioncode/florence_custom_uom1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="arvisioncode/florence_custom_uom1", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("arvisioncode/florence_custom_uom1", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("arvisioncode/florence_custom_uom1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use arvisioncode/florence_custom_uom1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arvisioncode/florence_custom_uom1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arvisioncode/florence_custom_uom1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arvisioncode/florence_custom_uom1

SGLang

How to use arvisioncode/florence_custom_uom1 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 "arvisioncode/florence_custom_uom1" \
    --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": "arvisioncode/florence_custom_uom1",
		"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 "arvisioncode/florence_custom_uom1" \
        --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": "arvisioncode/florence_custom_uom1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arvisioncode/florence_custom_uom1 with Docker Model Runner:
```
docker model run hf.co/arvisioncode/florence_custom_uom1
```

arvisioncode commited on Sep 18, 2024

Commit

d142326

verified ·

1 Parent(s): 72763f4

Update config.json

Browse files

Files changed (1) hide show

config.json +13 -13

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
   "ignore_index": -100,
   "model_type": "florence2",
   "pad_token_id": 1,
-  "projection_dim": 768,
   "text_config": {
       "vocab_size": 51289,
       "activation_dropout": 0.1,
@@ -23,18 +23,18 @@
       "bos_token_id": 0,
       "classif_dropout": 0.1,
       "classifier_dropout": 0.0,
-      "d_model": 768,
-      "decoder_attention_heads": 12,
-      "decoder_ffn_dim": 3072,
       "decoder_layerdrop": 0.0,
-      "decoder_layers": 6,
       "decoder_start_token_id": 2,
       "dropout": 0.1,
       "early_stopping": true,
-      "encoder_attention_heads": 12,
-      "encoder_ffn_dim": 3072,
       "encoder_layerdrop": 0.0,
-      "encoder_layers": 6,
       "eos_token_id": 2,
       "forced_eos_token_id": 2,
       "forced_bos_token_id": 0,
@@ -49,7 +49,7 @@
       "max_position_embeddings": 1024,
       "no_repeat_ngram_size": 3,
       "normalize_before": false,
-      "num_hidden_layers": 6,
       "pad_token_id": 1,
       "scale_embedding": false,
       "num_beams": 3
@@ -62,12 +62,12 @@
     "patch_padding": [3, 1, 1, 1],
     "patch_prenorm": [false, true, true, true],
     "enable_checkpoint": false,
-    "dim_embed": [128, 256, 512, 1024],
-    "num_heads": [4, 8, 16, 32],
-    "num_groups": [4, 8, 16, 32],
     "depths": [1, 1, 9, 1],
     "window_size": 12,
-    "projection_dim": 768,
     "visual_temporal_embedding": {
         "type": "COSINE",
         "max_temporal_embeddings": 100

   "ignore_index": -100,
   "model_type": "florence2",
   "pad_token_id": 1,
+  "projection_dim": 1024,
   "text_config": {
       "vocab_size": 51289,
       "activation_dropout": 0.1,
       "bos_token_id": 0,
       "classif_dropout": 0.1,
       "classifier_dropout": 0.0,
+      "d_model": 1024,
+      "decoder_attention_heads": 16,
+      "decoder_ffn_dim": 4096,
       "decoder_layerdrop": 0.0,
+      "decoder_layers": 12,
       "decoder_start_token_id": 2,
       "dropout": 0.1,
       "early_stopping": true,
+      "encoder_attention_heads": 16,
+      "encoder_ffn_dim": 4096,
       "encoder_layerdrop": 0.0,
+      "encoder_layers": 12,
       "eos_token_id": 2,
       "forced_eos_token_id": 2,
       "forced_bos_token_id": 0,
       "max_position_embeddings": 1024,
       "no_repeat_ngram_size": 3,
       "normalize_before": false,
+      "num_hidden_layers": 12,
       "pad_token_id": 1,
       "scale_embedding": false,
       "num_beams": 3
     "patch_padding": [3, 1, 1, 1],
     "patch_prenorm": [false, true, true, true],
     "enable_checkpoint": false,
+    "dim_embed": [256, 512, 1024, 2048],
+    "num_heads": [8, 16, 32, 64],
+    "num_groups": [8, 16, 32, 64],
     "depths": [1, 1, 9, 1],
     "window_size": 12,
+    "projection_dim": 1024,
     "visual_temporal_embedding": {
         "type": "COSINE",
         "max_temporal_embeddings": 100