Image-Text-to-Text
Safetensors
Spanish
ocr
receipt
invoice
vision
fine-tuned
unsloth
lora
json-extraction
Instructions to use Lacax/deepseek_ocr_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps
- Unsloth Studio
How to use Lacax/deepseek_ocr_lora with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Lacax/deepseek_ocr_lora to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Lacax/deepseek_ocr_lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Lacax/deepseek_ocr_lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Lacax/deepseek_ocr_lora", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,9 +36,9 @@ Dado una imagen de ticket o factura, el modelo devuelve un JSON con la siguiente
|
|
| 36 |
"comercio": "Nombre del establecimiento",
|
| 37 |
"fecha": "DD/MM/AAAA",
|
| 38 |
"cif": "B12345678",
|
| 39 |
-
"
|
| 40 |
{
|
| 41 |
-
"
|
| 42 |
"cantidad": 2,
|
| 43 |
"precio": 3.50
|
| 44 |
}
|
|
@@ -109,4 +109,4 @@ model = PeftModel.from_pretrained(model, LORA_ID)
|
|
| 109 |
|
| 110 |
## Autor
|
| 111 |
|
| 112 |
-
**
|
|
|
|
| 36 |
"comercio": "Nombre del establecimiento",
|
| 37 |
"fecha": "DD/MM/AAAA",
|
| 38 |
"cif": "B12345678",
|
| 39 |
+
"items": [
|
| 40 |
{
|
| 41 |
+
"descripcion": "Nombre del producto",
|
| 42 |
"cantidad": 2,
|
| 43 |
"precio": 3.50
|
| 44 |
}
|
|
|
|
| 109 |
|
| 110 |
## Autor
|
| 111 |
|
| 112 |
+
**Jonatan Thorpe Plaza** — Proyecto de estudio personal sobre fine-tuning de modelos de visión multimodal.
|