Image-Text-to-Text
Transformers
TensorBoard
Safetensors
pix2struct
Generated from Trainer
invoice-processing
information-extraction
czech-language
document-ai
multimodal-model
generative-model
synthetic-data
Instructions to use TomasFAV/Pix2StructCzechInvoiceV0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TomasFAV/Pix2StructCzechInvoiceV0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="TomasFAV/Pix2StructCzechInvoiceV0")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV0") model = AutoModelForImageTextToText.from_pretrained("TomasFAV/Pix2StructCzechInvoiceV0") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TomasFAV/Pix2StructCzechInvoiceV0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TomasFAV/Pix2StructCzechInvoiceV0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TomasFAV/Pix2StructCzechInvoiceV0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV0
- SGLang
How to use TomasFAV/Pix2StructCzechInvoiceV0 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 "TomasFAV/Pix2StructCzechInvoiceV0" \ --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": "TomasFAV/Pix2StructCzechInvoiceV0", "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 "TomasFAV/Pix2StructCzechInvoiceV0" \ --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": "TomasFAV/Pix2StructCzechInvoiceV0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TomasFAV/Pix2StructCzechInvoiceV0 with Docker Model Runner:
docker model run hf.co/TomasFAV/Pix2StructCzechInvoiceV0
Upload Pix2StructForConditionalGeneration
Browse files- config.json +5 -6
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -8,14 +8,14 @@
|
|
| 8 |
"initializer_factor": 1.0,
|
| 9 |
"initializer_range": 0.02,
|
| 10 |
"is_encoder_decoder": true,
|
| 11 |
-
"is_vqa":
|
| 12 |
"model_type": "pix2struct",
|
| 13 |
"pad_token_id": 0,
|
| 14 |
"text_config": {
|
| 15 |
"d_ff": 2048,
|
| 16 |
"d_kv": 64,
|
| 17 |
"dense_act_fn": "gelu_new",
|
| 18 |
-
"dropout_rate": 0.
|
| 19 |
"dtype": "float32",
|
| 20 |
"encoder_hidden_size": 768,
|
| 21 |
"hidden_size": 768,
|
|
@@ -29,18 +29,17 @@
|
|
| 29 |
"relative_attention_max_distance": 128,
|
| 30 |
"relative_attention_num_buckets": 32,
|
| 31 |
"use_cache": false,
|
| 32 |
-
"vocab_size":
|
| 33 |
},
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
"transformers_version": "4.57.3",
|
| 36 |
"vision_config": {
|
| 37 |
-
"attention_dropout": 0.
|
| 38 |
"d_ff": 2048,
|
| 39 |
"d_kv": 64,
|
| 40 |
"dense_act_fn": "gelu_new",
|
| 41 |
-
"dropout_rate": 0.
|
| 42 |
"dtype": "float32",
|
| 43 |
-
"hidden_dropout_prob": 0.2,
|
| 44 |
"hidden_size": 768,
|
| 45 |
"initializer_factor": 1.0,
|
| 46 |
"initializer_range": 0.02,
|
|
|
|
| 8 |
"initializer_factor": 1.0,
|
| 9 |
"initializer_range": 0.02,
|
| 10 |
"is_encoder_decoder": true,
|
| 11 |
+
"is_vqa": true,
|
| 12 |
"model_type": "pix2struct",
|
| 13 |
"pad_token_id": 0,
|
| 14 |
"text_config": {
|
| 15 |
"d_ff": 2048,
|
| 16 |
"d_kv": 64,
|
| 17 |
"dense_act_fn": "gelu_new",
|
| 18 |
+
"dropout_rate": 0.1,
|
| 19 |
"dtype": "float32",
|
| 20 |
"encoder_hidden_size": 768,
|
| 21 |
"hidden_size": 768,
|
|
|
|
| 29 |
"relative_attention_max_distance": 128,
|
| 30 |
"relative_attention_num_buckets": 32,
|
| 31 |
"use_cache": false,
|
| 32 |
+
"vocab_size": 50432
|
| 33 |
},
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
"transformers_version": "4.57.3",
|
| 36 |
"vision_config": {
|
| 37 |
+
"attention_dropout": 0.0,
|
| 38 |
"d_ff": 2048,
|
| 39 |
"d_kv": 64,
|
| 40 |
"dense_act_fn": "gelu_new",
|
| 41 |
+
"dropout_rate": 0.0,
|
| 42 |
"dtype": "float32",
|
|
|
|
| 43 |
"hidden_size": 768,
|
| 44 |
"initializer_factor": 1.0,
|
| 45 |
"initializer_range": 0.02,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3eeae59c802767ff7b3dddca23794a977784ccdccc08b452c09131234110ca7
|
| 3 |
+
size 1130333048
|