Instructions to use baconnier/deepsynth-ocr-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use baconnier/deepsynth-ocr-finetuned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-OCR")
model = PeftModel.from_pretrained(base_model, "baconnier/deepsynth-ocr-finetuned")

Transformers

How to use baconnier/deepsynth-ocr-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="baconnier/deepsynth-ocr-finetuned")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("baconnier/deepsynth-ocr-finetuned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use baconnier/deepsynth-ocr-finetuned with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/baconnier/deepsynth-ocr-finetuned

SGLang

How to use baconnier/deepsynth-ocr-finetuned 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 "baconnier/deepsynth-ocr-finetuned" \
    --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": "baconnier/deepsynth-ocr-finetuned",
		"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 "baconnier/deepsynth-ocr-finetuned" \
        --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": "baconnier/deepsynth-ocr-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use baconnier/deepsynth-ocr-finetuned with Docker Model Runner:
```
docker model run hf.co/baconnier/deepsynth-ocr-finetuned
```

baconnier commited on Nov 3, 2025

Commit

a0ed4e6

verified ·

1 Parent(s): 4328d65

Upload metrics.json

Browse files

Files changed (1) hide show

metrics.json +9 -9

metrics.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "config": {
     "model_name": "deepseek-ai/DeepSeek-OCR",
     "output_dir": "/app/trained_model",
-    "batch_size": 2,
     "num_epochs": 3,
-    "gradient_accumulation_steps": 4,
     "max_length": 512,
     "mixed_precision": "bf16",
     "optimizer": {
@@ -63,15 +63,15 @@
     "use_text_projection": false
   },
   "metrics": {
-    "train_loss": 2.18429114023149,
     "train_loss_per_epoch": [
-      2.3577296189427375,
-      2.2400757206499575,
-      2.18429114023149
     ],
     "epochs": 3,
-    "total_steps": 30000,
-    "eval_loss": 2.7863627457618714,
-    "eval_perplexity": 16.22190915889909
   }
 }

   "config": {
     "model_name": "deepseek-ai/DeepSeek-OCR",
     "output_dir": "/app/trained_model",
+    "batch_size": 6,
     "num_epochs": 3,
+    "gradient_accumulation_steps": 2,
     "max_length": 512,
     "mixed_precision": "bf16",
     "optimizer": {
     "use_text_projection": false
   },
   "metrics": {
+    "train_loss": 2.176753851794596,
     "train_loss_per_epoch": [
+      2.334065725453685,
+      2.2217297172861037,
+      2.176753851794596
     ],
     "epochs": 3,
+    "total_steps": 10002,
+    "eval_loss": 2.795014963263557,
+    "eval_perplexity": 16.362873593315534
   }
 }