Instructions to use ariG23498/tiny-pali-gemma-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ariG23498/tiny-pali-gemma-test with Transformers:

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

pipe = pipeline("image-text-to-text", model="ariG23498/tiny-pali-gemma-test")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ariG23498/tiny-pali-gemma-test")
model = AutoModelForImageTextToText.from_pretrained("ariG23498/tiny-pali-gemma-test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ariG23498/tiny-pali-gemma-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ariG23498/tiny-pali-gemma-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ariG23498/tiny-pali-gemma-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ariG23498/tiny-pali-gemma-test

SGLang

How to use ariG23498/tiny-pali-gemma-test 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 "ariG23498/tiny-pali-gemma-test" \
    --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": "ariG23498/tiny-pali-gemma-test",
		"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 "ariG23498/tiny-pali-gemma-test" \
        --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": "ariG23498/tiny-pali-gemma-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ariG23498/tiny-pali-gemma-test with Docker Model Runner:
```
docker model run hf.co/ariG23498/tiny-pali-gemma-test
```

ariG23498 HF Staff commited on Jul 7, 2024

Commit

d3f23e7

verified ·

1 Parent(s): ee1c4c1

Upload PaliGemmaForConditionalGeneration

Browse files

Files changed (4) hide show

config.json +2 -2
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +2 -2
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "image_token_index": 257152,
   "model_type": "paligemma",
   "pad_token_id": 0,
-  "projection_dim": 2048,
   "text_config": {
     "hidden_size": 32,
     "intermediate_size": 32,
@@ -33,7 +33,7 @@
     "num_hidden_layers": 1,
     "num_image_tokens": 256,
     "patch_size": 14,
-    "projection_dim": 2048,
     "projector_hidden_act": "gelu_fast",
     "vision_use_head": false
   },

   "image_token_index": 257152,
   "model_type": "paligemma",
   "pad_token_id": 0,
+  "projection_dim": 32,
   "text_config": {
     "hidden_size": 32,
     "intermediate_size": 32,
     "num_hidden_layers": 1,
     "num_image_tokens": 256,
     "patch_size": 14,
+    "projection_dim": 32,
     "projector_hidden_act": "gelu_fast",
     "vision_use_head": false
   },

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ab4716d41209c78e3eaa96535ef104785bf8937324b1944e106c67fd825014
 size 32923800

 version https://git-lfs.github.com/spec/v1
+oid sha256:facb506651aab3a7f3a095a2c724c15fbeff8dfe4e594421db2f5b9ed53154e6
 size 32923800

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219755e92f6d41eac3e403990b5187a46df3f2a8ea78870648f04df8755a3fe6
-size 1011104

 version https://git-lfs.github.com/spec/v1
+oid sha256:94927467303e1e2b226d54b4cbec0f95e95fe91da74bd1034b5e97aa79292f2c
+size 744984

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 33930752
   },
   "weight_map": {
     "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",

 {
   "metadata": {
+    "total_size": 33664640
   },
   "weight_map": {
     "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",