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

Libraries

How to use Elamranilyas/modataDONUT with Transformers:

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

pipe = pipeline("image-text-to-text", model="Elamranilyas/modataDONUT")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Elamranilyas/modataDONUT")
model = AutoModelForMultimodalLM.from_pretrained("Elamranilyas/modataDONUT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Elamranilyas/modataDONUT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Elamranilyas/modataDONUT

SGLang

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

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

Elamranilyas commited on Jul 30, 2023

Commit

04dbda1

1 Parent(s): 0f4bd04

Training in progress, epoch 0

Browse files

Files changed (3) hide show

config.json +2 -2
generation_config.json +1 -1
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -83,7 +83,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.29.2",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
@@ -180,7 +180,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.29.2",
     "typical_p": 1.0,
     "use_absolute_embeddings": false,
     "use_bfloat16": false,

     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
+    "transformers_version": "4.30.2",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
+    "transformers_version": "4.30.2",
     "typical_p": 1.0,
     "use_absolute_embeddings": false,
     "use_bfloat16": false,

generation_config.json CHANGED Viewed

@@ -6,5 +6,5 @@
   "forced_eos_token_id": 2,
   "max_length": 768,
   "pad_token_id": 1,
-  "transformers_version": "4.29.2"
 }

   "forced_eos_token_id": 2,
   "max_length": 768,
   "pad_token_id": 1,
+  "transformers_version": "4.30.2"
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb39d1c5db5e284c92a396dab6793166b8f4fc0874e55d1b887868dcc7e4ff7f
 size 809232153

 version https://git-lfs.github.com/spec/v1
+oid sha256:1ec9c6ec0df7a64c2d37f26b9dec928e1e2bfcce31182c53e1eabda275de258e
 size 809232153