Instructions to use hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration")
model = AutoModelForImageTextToText.from_pretrained("hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration")

Transformers.js

How to use hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration with Transformers.js:

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

// Allocate pipeline
const pipe = await pipeline('image-text-to-text', 'hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration');

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration

SGLang

How to use hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration 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 "hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration" \
    --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": "hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration",
		"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 "hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration" \
        --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": "hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-PaliGemmaForConditionalGeneration
```

Upload 11 files

by Xenova HF Staff - opened Dec 6, 2024

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

+10

-9

Files changed (4) hide show

config.json +6 -5
generation_config.json +1 -1
onnx/decoder_model_merged.onnx +2 -2
onnx/vision_encoder.onnx +1 -1

config.json CHANGED Viewed

@@ -1,4 +1,6 @@
 {
   "_vocab_size": 257152,
   "architectures": [
     "PaliGemmaForConditionalGeneration"
@@ -11,19 +13,18 @@
   "pad_token_id": 0,
   "projection_dim": 16,
   "text_config": {
-    "head_dim": 256,
     "hidden_size": 16,
     "intermediate_size": 16,
     "model_type": "gemma",
-    "max_position_embeddings": 8192,
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
     "num_image_tokens": 256,
     "num_key_value_heads": 1,
-    "vocab_size": 257216
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.47.0.dev0",
   "vision_config": {
     "hidden_size": 16,
     "intermediate_size": 32,
@@ -36,4 +37,4 @@
     "projector_hidden_act": "gelu_fast",
     "vision_use_head": false
   }
-}

 {
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Xenova/tiny-random-PaliGemmaForConditionalGeneration",
   "_vocab_size": 257152,
   "architectures": [
     "PaliGemmaForConditionalGeneration"
   "pad_token_id": 0,
   "projection_dim": 16,
   "text_config": {
     "hidden_size": 16,
     "intermediate_size": 16,
     "model_type": "gemma",
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
     "num_image_tokens": 256,
     "num_key_value_heads": 1,
+    "vocab_size": 257216,
+    "head_dim": 256
   },
   "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
   "vision_config": {
     "hidden_size": 16,
     "intermediate_size": 32,
     "projector_hidden_act": "gelu_fast",
     "vision_use_head": false
   }
+}

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.47.0.dev0"
 }

   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
+  "transformers_version": "4.48.0.dev0"
 }

onnx/decoder_model_merged.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352ef053857cb6d609cfbea476c417103ca2a802460bcf6fb1603947c448f474
-size 16923643

 version https://git-lfs.github.com/spec/v1
+oid sha256:f94b7e5203e77a7a1b0b2887556753aabd2416aeda7b855d1b43398c97ff1f29
+size 16861777

onnx/vision_encoder.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c364818d96d685107d38e1a5451b1ae62d9310ff5f6701d89f79f628cdb70c
 size 120673

 version https://git-lfs.github.com/spec/v1
+oid sha256:916d69fe0fcf0204bf55d293e30ecff6bb62b6d022fae6bcfc7dae039e3a6497
 size 120673