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

Libraries

How to use tachiwin/paddleocr_multilingual_checkpoints_c 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_c", trust_remote_code=True)
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("tachiwin/paddleocr_multilingual_checkpoints_c", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("tachiwin/paddleocr_multilingual_checkpoints_c", trust_remote_code=True)
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_c 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_c"
# 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_c",
		"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_c

SGLang

How to use tachiwin/paddleocr_multilingual_checkpoints_c 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_c" \
    --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_c",
		"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_c" \
        --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_c",
		"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_c 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_c 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_c 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_c 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_c",
    max_seq_length=2048,
)

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

ljcamargo commited on Jan 10

Commit

22e9de9

verified ·

1 Parent(s): 29d0009

Training in progress, step 3500, 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 +178 -3

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc90e72e9df06c7a8b2859568abbda018ecb77710946f3069e0c35fa974f19ee
 size 3809184360

 version https://git-lfs.github.com/spec/v1
+oid sha256:ca1d58e2cd18a1fc09601b5143bb78b5307a273e6e2f1750228c18041d7fe77e
 size 3809184360

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655084455e5e897aa7ef7acbe8b134c275ee59dd5ff109b69ff76cd085fd6e07
 size 2458291491

 version https://git-lfs.github.com/spec/v1
+oid sha256:3d9b3bc32af7a9c7224769cd6c49a9680aa7f8795c0d4e082d32018b4c599ff6
 size 2458291491

last-checkpoint/scaler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea341a3d505626ad57a03d7f2e993437556ed56796356e3afaa8f1db62445455
 size 1383

 version https://git-lfs.github.com/spec/v1
+oid sha256:d8841fa7aad843ffcf2b76d868211d81553f8ce267313764fca81be4f5b42b4d
 size 1383

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc273b404670a1098fedda6e7c02f1509edb236f0c25d50ae9fbf6dd87e347b
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:1c493c177a6a7b8f4b53d9f320f001568436248d37644f960edb69a4818ec2df
 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": 0.8666666666666667,
   "eval_steps": 500,
-  "global_step": 3250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2283,6 +2283,181 @@
       "learning_rate": 6.805929919137468e-06,
       "loss": 0.2464,
       "step": 3250
     }
   ],
   "logging_steps": 10,
@@ -2302,7 +2477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.87649798448128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.9333333333333333,
   "eval_steps": 500,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "learning_rate": 6.805929919137468e-06,
       "loss": 0.2464,
       "step": 3250
+    },
+    {
+      "epoch": 0.8693333333333333,
+      "grad_norm": 5.073930740356445,
+      "learning_rate": 6.671159029649596e-06,
+      "loss": 0.2491,
+      "step": 3260
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 6.984921932220459,
+      "learning_rate": 6.536388140161725e-06,
+      "loss": 0.2212,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 5.525951862335205,
+      "learning_rate": 6.401617250673856e-06,
+      "loss": 0.2446,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8773333333333333,
+      "grad_norm": 5.485599040985107,
+      "learning_rate": 6.266846361185984e-06,
+      "loss": 0.2735,
+      "step": 3290
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.451603889465332,
+      "learning_rate": 6.132075471698113e-06,
+      "loss": 0.2499,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8826666666666667,
+      "grad_norm": 8.449997901916504,
+      "learning_rate": 5.997304582210243e-06,
+      "loss": 0.262,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8853333333333333,
+      "grad_norm": 2.8802688121795654,
+      "learning_rate": 5.862533692722373e-06,
+      "loss": 0.248,
+      "step": 3320
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 6.58447790145874,
+      "learning_rate": 5.727762803234501e-06,
+      "loss": 0.1707,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8906666666666667,
+      "grad_norm": 10.708820343017578,
+      "learning_rate": 5.592991913746631e-06,
+      "loss": 0.2294,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 8.319356918334961,
+      "learning_rate": 5.458221024258761e-06,
+      "loss": 0.2165,
+      "step": 3350
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 6.977818012237549,
+      "learning_rate": 5.3234501347708894e-06,
+      "loss": 0.2321,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8986666666666666,
+      "grad_norm": 6.978248119354248,
+      "learning_rate": 5.188679245283019e-06,
+      "loss": 0.2039,
+      "step": 3370
+    },
+    {
+      "epoch": 0.9013333333333333,
+      "grad_norm": 7.0379438400268555,
+      "learning_rate": 5.053908355795149e-06,
+      "loss": 0.2364,
+      "step": 3380
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 5.10407018661499,
+      "learning_rate": 4.9191374663072775e-06,
+      "loss": 0.3408,
+      "step": 3390
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 4.217552185058594,
+      "learning_rate": 4.784366576819407e-06,
+      "loss": 0.1653,
+      "step": 3400
+    },
+    {
+      "epoch": 0.9093333333333333,
+      "grad_norm": 8.982743263244629,
+      "learning_rate": 4.649595687331537e-06,
+      "loss": 0.208,
+      "step": 3410
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 7.103553295135498,
+      "learning_rate": 4.5148247978436664e-06,
+      "loss": 0.1838,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9146666666666666,
+      "grad_norm": 6.565107822418213,
+      "learning_rate": 4.380053908355795e-06,
+      "loss": 0.2254,
+      "step": 3430
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 8.163582801818848,
+      "learning_rate": 4.245283018867925e-06,
+      "loss": 0.1598,
+      "step": 3440
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.565555095672607,
+      "learning_rate": 4.1105121293800545e-06,
+      "loss": 0.1888,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9226666666666666,
+      "grad_norm": 7.8352508544921875,
+      "learning_rate": 3.975741239892183e-06,
+      "loss": 0.2683,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9253333333333333,
+      "grad_norm": 8.402386665344238,
+      "learning_rate": 3.840970350404313e-06,
+      "loss": 0.1869,
+      "step": 3470
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 8.078757286071777,
+      "learning_rate": 3.706199460916442e-06,
+      "loss": 0.2293,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9306666666666666,
+      "grad_norm": 7.771483898162842,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.3479,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 3.739326000213623,
+      "learning_rate": 3.436657681940701e-06,
+      "loss": 0.1441,
+      "step": 3500
     }
   ],
   "logging_steps": 10,
       "attributes": {}
     }
   },
+  "total_flos": 6.32834922129408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null