Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Instructions to use mo-thecreator/ViT-GPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mo-thecreator/ViT-GPT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="mo-thecreator/ViT-GPT2")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("mo-thecreator/ViT-GPT2") model = AutoModelForImageTextToText.from_pretrained("mo-thecreator/ViT-GPT2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use mo-thecreator/ViT-GPT2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mo-thecreator/ViT-GPT2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mo-thecreator/ViT-GPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mo-thecreator/ViT-GPT2
- SGLang
How to use mo-thecreator/ViT-GPT2 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 "mo-thecreator/ViT-GPT2" \ --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": "mo-thecreator/ViT-GPT2", "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 "mo-thecreator/ViT-GPT2" \ --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": "mo-thecreator/ViT-GPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mo-thecreator/ViT-GPT2 with Docker Model Runner:
docker model run hf.co/mo-thecreator/ViT-GPT2
Mohammed Abdeldayem commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: ViT-GPT2
|
| 7 |
results: []
|
|
@@ -59,4 +61,4 @@ The following hyperparameters were used during training:
|
|
| 59 |
- Transformers 4.44.2
|
| 60 |
- Pytorch 2.4.0
|
| 61 |
- Datasets 3.0.0
|
| 62 |
-
- Tokenizers 0.19.1
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
- image-to-text
|
| 6 |
+
- image-captioning
|
| 7 |
model-index:
|
| 8 |
- name: ViT-GPT2
|
| 9 |
results: []
|
|
|
|
| 61 |
- Transformers 4.44.2
|
| 62 |
- Pytorch 2.4.0
|
| 63 |
- Datasets 3.0.0
|
| 64 |
+
- Tokenizers 0.19.1
|