update configs and tokenizer

README.md

@@ -69,107 +69,13 @@ Compared with model-only inference, the SDK integrates PP-DocLayoutV3 and provid
 
 Note that the SDK is currently designed for document parsing tasks only. For information extraction tasks, please refer to the following section and run inference directly with the model.
 
-### vLLM
+### Serve GLM-OCR Locally
 
-1. run 
+GLM-OCR supports deployment with the following frameworks. Feel free to try them out:
 
-```bash
-pip install -U vllm --extra-index-url https://wheels.vllm.ai/nightly
-```
-
-or using docker with:
-```
-docker pull vllm/vllm-openai:nightly
-```
-
-2. run with:
-
-```bash
-pip install git+https://github.com/huggingface/transformers.git
-vllm serve zai-org/GLM-OCR  --allowed-local-media-path /  --port 8080
-```
-
-### SGLang
-
-
-1. using docker with:
-
-```bash
-docker pull lmsysorg/sglang:dev
-```
-
-or build it from source with:
-
-```bash
-pip install git+https://github.com/sgl-project/sglang.git#subdirectory=python
-```
-
-2. run with:
-
-```bash
-pip install git+https://github.com/huggingface/transformers.git
-python -m sglang.launch_server --model zai-org/GLM-OCR --port 8080
-```
-
-### Ollama 
-
-1. Download [Ollama](https://ollama.com/download).
-2. run with: 
-
-```bash
-ollama run glm-ocr
-```
-
-Ollama will automatically use image file path when an image is dragged into the terminal: 
-
-```bash
-ollama run glm-ocr Text Recognition: ./image.png
-```
-
-### Transformers
-
-```
-pip install git+https://github.com/huggingface/transformers.git
-```
-
-```python
-from transformers import AutoProcessor, AutoModelForImageTextToText
-import torch
-
-MODEL_PATH = "zai-org/GLM-OCR"
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {
-                "type": "image",
-                "url": "test_image.png"
-            },
-            {
-                "type": "text",
-                "text": "Text Recognition:"
-            }
-        ],
-    }
-]
-processor = AutoProcessor.from_pretrained(MODEL_PATH)
-model = AutoModelForImageTextToText.from_pretrained(
-    pretrained_model_name_or_path=MODEL_PATH,
-    torch_dtype="auto",
-    device_map="auto",
-)
-inputs = processor.apply_chat_template(
-    messages,
-    tokenize=True,
-    add_generation_prompt=True,
-    return_dict=True,
-    return_tensors="pt"
-).to(model.device)
-inputs.pop("token_type_ids", None)
-generated_ids = model.generate(**inputs, max_new_tokens=8192)
-output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
-print(output_text)
-```
+- [SGLang](https://github.com/sgl-project/sglang) — see [cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-OCR)
+- [vLLM](https://github.com/vllm-project/vllm) — see [recipes](https://recipes.vllm.ai/zai-org/GLM-OCR)
+- [Transformers](https://github.com/huggingface/transformers) — see [transformers docs](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/glm_ocr.md)
 
 ### Prompt Limited
 

config.json

@@ -2,64 +2,71 @@
   "architectures": [
     "GlmOcrForConditionalGeneration"
   ],
+  "image_end_token_id": 59257,
+  "image_start_token_id": 59256,
+  "image_token_id": 59280,
   "model_type": "glm_ocr",
   "text_config": {
-    "model_type": "glm_ocr_text",
-    "pad_token_id": 59246,
-    "vocab_size": 59392,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
     "eos_token_id": [
       59246,
       59253
     ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
     "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 1536,
     "initializer_range": 0.02,
     "intermediate_size": 4608,
     "max_position_embeddings": 131072,
+    "model_type": "glm_ocr_text",
     "num_attention_heads": 16,
     "num_hidden_layers": 16,
-    "num_nextn_predict_layers": 1,
     "num_key_value_heads": 8,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 59246,
     "rms_norm_eps": 1e-05,
-    "dtype": "bfloat16",
     "rope_parameters": {
-      "rope_type": "default",
       "mrope_section": [
         16,
         24,
         24
       ],
-       "partial_rotary_factor": 1.0,
-       "rope_theta": 10000
+      "partial_rotary_factor": 1.0,
+      "rope_theta": 10000,
+      "rope_type": "default"
     },
     "tie_word_embeddings": false,
-    "use_cache": true
+    "use_cache": true,
+    "vocab_size": 59392
   },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.17.0",
+  "video_end_token_id": 59259,
+  "video_start_token_id": 59258,
+  "video_token_id": 59281,
   "vision_config": {
-    "model_type": "glm_ocr_vision",
-    "hidden_size": 1024,
-    "depth": 24,
-    "num_heads": 16,
     "attention_bias": true,
-    "intermediate_size": 4096,
+    "attention_dropout": 0.0,
+    "depth": 24,
     "hidden_act": "silu",
     "hidden_dropout_prob": 0.0,
-    "initializer_range": 0.02,
+    "hidden_size": 1024,
     "image_size": 336,
-    "patch_size": 14,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "glm_ocr_vision",
+    "num_heads": 16,
     "out_hidden_size": 1536,
+    "patch_size": 14,
     "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "axial"
+    },
     "spatial_merge_size": 2,
     "temporal_patch_size": 2
-  },
-  "image_start_token_id": 59256,
-  "image_end_token_id": 59257,
-  "video_start_token_id": 59258,
-  "video_end_token_id": 59259,
-  "image_token_id": 59280,
-  "video_token_id": 59281,
-  "transformers_version": "5.0.1dev0"
+  }
 }

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Glm46VImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 9633792,
+      "shortest_edge": 12544
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Glm46VProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_duration": 300,
+    "max_image_size": {
+      "longest_edge": 47040000
+    },
+    "merge_size": 2,
+    "num_frames": 16,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 9633792,
+      "shortest_edge": 12544
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Glm46VVideoProcessor"
+  }
+}

tokenizer_config.json

@@ -36,12 +36,13 @@
     "</arg_value>",
     "/nothink",
     "<|begin_of_box|>",
-    "<|end_of_box|>",
-    "<|image|>",
-    "<|video|>"
+    "<|end_of_box|>"
   ],
   "is_local": true,
   "model_max_length": 655380,
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "model_specific_special_tokens": {},
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "processor_class": "Glm46VProcessor",