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

Libraries

How to use tachiwin/paddleocr_multilingual_checkpoints with Transformers:

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

pipe = pipeline("image-text-to-text", model="tachiwin/paddleocr_multilingual_checkpoints", trust_remote_code=True, device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("tachiwin/paddleocr_multilingual_checkpoints", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("tachiwin/paddleocr_multilingual_checkpoints", trust_remote_code=True, device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tachiwin/paddleocr_multilingual_checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tachiwin/paddleocr_multilingual_checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tachiwin/paddleocr_multilingual_checkpoints",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/tachiwin/paddleocr_multilingual_checkpoints

SGLang

How to use tachiwin/paddleocr_multilingual_checkpoints 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 "tachiwin/paddleocr_multilingual_checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tachiwin/paddleocr_multilingual_checkpoints",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "tachiwin/paddleocr_multilingual_checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tachiwin/paddleocr_multilingual_checkpoints",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use tachiwin/paddleocr_multilingual_checkpoints 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 tachiwin/paddleocr_multilingual_checkpoints 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 tachiwin/paddleocr_multilingual_checkpoints to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tachiwin/paddleocr_multilingual_checkpoints to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="tachiwin/paddleocr_multilingual_checkpoints",
    max_seq_length=2048,
)

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

ljcamargo commited on Dec 21, 2025

Commit

c3d91f6

verified ·

1 Parent(s): 2462ee6

Training in progress, step 1000, checkpoint

Browse files

Files changed (5) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/scaler.pt +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +73 -3

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f464bb34c079c49fc4894f86d25745fe89898016c82a86a608f7319e127060fb
 size 3826461296

 version https://git-lfs.github.com/spec/v1
+oid sha256:d32ac3feded5c3479ac17b89c6c7d6fc8a6a5c9e382b0cd178658d12631f6320
 size 3826461296

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a0275491ae162fc646c048a499bb9160456c508f7be5abff3710269e6fdf4a
 size 2479955235

 version https://git-lfs.github.com/spec/v1
+oid sha256:66774c6e05115bebae2c4f1d957fbbf1529b4a28c6a6bf08a7cad3ceb574a9aa
 size 2479955235

last-checkpoint/scaler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504b7bc543b9e5f039f6559d07b099507a66c15c86836ff5981e4eee51792c02
 size 1383

 version https://git-lfs.github.com/spec/v1
+oid sha256:e41f9a9fd18b485398505f595af3510abbf13d7745049b3d74379645d85abae1
 size 1383

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb268d80dcd8f32a0b291e0f300bdc2df3898cc3661ea44beb8067d70741b7b
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd6ac75c94c2f7dfcfe42f00a66031ae062ed94adea9b80ebcb8b3240ad4424c
 size 1465

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36,
   "eval_steps": 500,
-  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -638,6 +638,76 @@
       "learning_rate": 3.22347266881029e-05,
       "loss": 0.625,
       "step": 900
     }
   ],
   "logging_steps": 10,
@@ -657,7 +727,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6191274912395264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.4,
   "eval_steps": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "learning_rate": 3.22347266881029e-05,
       "loss": 0.625,
       "step": 900
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 23.470478057861328,
+      "learning_rate": 3.2033762057877816e-05,
+      "loss": 0.9571,
+      "step": 910
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 31.515092849731445,
+      "learning_rate": 3.1832797427652735e-05,
+      "loss": 0.7395,
+      "step": 920
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 14.246073722839355,
+      "learning_rate": 3.1631832797427654e-05,
+      "loss": 0.6884,
+      "step": 930
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 25.352590560913086,
+      "learning_rate": 3.143086816720258e-05,
+      "loss": 0.772,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 14.441354751586914,
+      "learning_rate": 3.12299035369775e-05,
+      "loss": 0.7406,
+      "step": 950
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 29.33234405517578,
+      "learning_rate": 3.102893890675242e-05,
+      "loss": 0.7242,
+      "step": 960
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 16.018104553222656,
+      "learning_rate": 3.0827974276527335e-05,
+      "loss": 0.9183,
+      "step": 970
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 14.766180992126465,
+      "learning_rate": 3.0627009646302254e-05,
+      "loss": 0.8971,
+      "step": 980
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 10.733450889587402,
+      "learning_rate": 3.042604501607717e-05,
+      "loss": 0.5546,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 15.318602561950684,
+      "learning_rate": 3.0225080385852088e-05,
+      "loss": 0.7582,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
       "attributes": {}
     }
   },
+  "total_flos": 1.7984652389369856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null