Instructions to use Gopal2002/donut_fix_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gopal2002/donut_fix_1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Gopal2002/donut_fix_1", device_map="auto")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Gopal2002/donut_fix_1") model = AutoModelForMultimodalLM.from_pretrained("Gopal2002/donut_fix_1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Gopal2002/donut_fix_1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gopal2002/donut_fix_1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gopal2002/donut_fix_1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Gopal2002/donut_fix_1
- SGLang
How to use Gopal2002/donut_fix_1 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 "Gopal2002/donut_fix_1" \ --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": "Gopal2002/donut_fix_1", "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 "Gopal2002/donut_fix_1" \ --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": "Gopal2002/donut_fix_1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Gopal2002/donut_fix_1 with Docker Model Runner:
docker model run hf.co/Gopal2002/donut_fix_1
Upload config
Browse files- config.json +1 -4
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "nielsr/donut-base",
|
| 3 |
"architectures": [
|
| 4 |
"VisionEncoderDecoderModel"
|
| 5 |
],
|
|
@@ -85,9 +84,8 @@
|
|
| 85 |
"typical_p": 1.0,
|
| 86 |
"use_bfloat16": false,
|
| 87 |
"use_cache": true,
|
| 88 |
-
"vocab_size":
|
| 89 |
},
|
| 90 |
-
"decoder_start_token_id": 57530,
|
| 91 |
"encoder": {
|
| 92 |
"_name_or_path": "",
|
| 93 |
"add_cross_attention": false,
|
|
@@ -185,7 +183,6 @@
|
|
| 185 |
},
|
| 186 |
"is_encoder_decoder": true,
|
| 187 |
"model_type": "vision-encoder-decoder",
|
| 188 |
-
"pad_token_id": 1,
|
| 189 |
"tie_word_embeddings": false,
|
| 190 |
"torch_dtype": "float32",
|
| 191 |
"transformers_version": "4.36.2"
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"VisionEncoderDecoderModel"
|
| 4 |
],
|
|
|
|
| 84 |
"typical_p": 1.0,
|
| 85 |
"use_bfloat16": false,
|
| 86 |
"use_cache": true,
|
| 87 |
+
"vocab_size": 57525
|
| 88 |
},
|
|
|
|
| 89 |
"encoder": {
|
| 90 |
"_name_or_path": "",
|
| 91 |
"add_cross_attention": false,
|
|
|
|
| 183 |
},
|
| 184 |
"is_encoder_decoder": true,
|
| 185 |
"model_type": "vision-encoder-decoder",
|
|
|
|
| 186 |
"tie_word_embeddings": false,
|
| 187 |
"torch_dtype": "float32",
|
| 188 |
"transformers_version": "4.36.2"
|