Instructions to use axteam/PaddleOCR-VL-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use axteam/PaddleOCR-VL-FP8-dynamic with Transformers:

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

pipe = pipeline("image-text-to-text", model="axteam/PaddleOCR-VL-FP8-dynamic", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("axteam/PaddleOCR-VL-FP8-dynamic", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("axteam/PaddleOCR-VL-FP8-dynamic", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use axteam/PaddleOCR-VL-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "axteam/PaddleOCR-VL-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "axteam/PaddleOCR-VL-FP8-dynamic",
		"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/axteam/PaddleOCR-VL-FP8-dynamic

SGLang

How to use axteam/PaddleOCR-VL-FP8-dynamic 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 "axteam/PaddleOCR-VL-FP8-dynamic" \
    --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": "axteam/PaddleOCR-VL-FP8-dynamic",
		"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 "axteam/PaddleOCR-VL-FP8-dynamic" \
        --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": "axteam/PaddleOCR-VL-FP8-dynamic",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use axteam/PaddleOCR-VL-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/axteam/PaddleOCR-VL-FP8-dynamic
```

PaddleOCR-VL-FP8-dynamic / config.json

uzins

Add files using upload-large-folder tool

719050d verified 3 days ago

Raw History Blame Contribute Delete

3.43 kB

{
  "architectures": [
    "PaddleOCRVLForConditionalGeneration"
  ],
  "attention_probs_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
    "AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"
  },
  "compression_ratio": 1.0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 1024,
  "ignored_index": -100,
  "image_token_id": 100295,
  "intermediate_size": 3072,
  "max_position_embeddings": 131072,
  "max_sequence_length": null,
  "model_type": "paddleocr_vl",
  "num_attention_heads": 16,
  "num_hidden_layers": 18,
  "num_key_value_heads": 2,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 500000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.0",
  "use_bias": false,
  "use_cache": false,
  "use_flash_attention": false,
  "video_token_id": 101307,
  "vision_config": {
    "architectures": [
      "PaddleOCRVisionModel"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
      "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
      "AutoModel": "modeling_paddleocr_vl.PaddleOCRVisionModel"
    },
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "paddleocr_vl",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "pad_token_id": 0,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2,
    "tokens_per_second": 2,
    "torch_dtype": "bfloat16"
  },
  "vision_start_token_id": 101305,
  "vision_end_token_id": 101306,
  "vocab_size": 103424,
  "weight_share_add_bias": true,
  "use_3d_rope": true,
  "rope_is_neox_style": true,
  "quantization_config": {
    "config_groups": {
      "FP8_DYNAMIC": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "token",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head",
      "re:.*embed_tokens.*",
      "re:visual\\..*",
      "re:mlp_AR\\..*",
      "re:.*norm.*"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "transform_config": {},
    "version": "0.19.0"
  }
}

	{
	"architectures": [
	"PaddleOCRVLForConditionalGeneration"
	],
	"attention_probs_dropout_prob": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
	"AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",
	"AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"
	},
	"compression_ratio": 1.0,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_dropout_prob": 0.0,
	"hidden_size": 1024,
	"ignored_index": -100,
	"image_token_id": 100295,
	"intermediate_size": 3072,
	"max_position_embeddings": 131072,
	"max_sequence_length": null,
	"model_type": "paddleocr_vl",
	"num_attention_heads": 16,
	"num_hidden_layers": 18,
	"num_key_value_heads": 2,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"mrope_section": [
	16,
	24,
	24
	],
	"rope_type": "default",
	"type": "default"
	},
	"rope_theta": 500000,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.55.0",
	"use_bias": false,
	"use_cache": false,
	"use_flash_attention": false,
	"video_token_id": 101307,
	"vision_config": {
	"architectures": [
	"PaddleOCRVisionModel"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
	"AutoModel": "modeling_paddleocr_vl.PaddleOCRVisionModel"
	},
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"image_size": 384,
	"intermediate_size": 4304,
	"layer_norm_eps": 1e-06,
	"model_type": "paddleocr_vl",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"pad_token_id": 0,
	"patch_size": 14,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2,
	"tokens_per_second": 2,
	"torch_dtype": "bfloat16"
	},
	"vision_start_token_id": 101305,
	"vision_end_token_id": 101306,
	"vocab_size": 103424,
	"weight_share_add_bias": true,
	"use_3d_rope": true,
	"rope_is_neox_style": true,
	"quantization_config": {
	"config_groups": {
	"FP8_DYNAMIC": {
	"format": "float-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": null,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "token",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "channel",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "float-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"lm_head",
	"re:.embed_tokens.",
	"re:visual\\..*",
	"re:mlp_AR\\..*",
	"re:.norm."
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"transform_config": {},
	"version": "0.19.0"
	}
	}