视频推理

README.md

@@ -61,7 +61,7 @@ messages = [
         "content": [
             {
                 "type": "image",
-                "url": "https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png"
+                "url": "https://model-demo.oss-cn-hangzhou.aliyuncs.com/Grayscale_8bits_palette_sample_image.png"
             },
             {
                 "type": "text",
@@ -70,12 +70,13 @@ messages = [
         ],
     }
 ]
-processor = AutoProcessor.from_pretrained(MODEL_PATH, use_fast=True)
 model = Glm4vForConditionalGeneration.from_pretrained(
     pretrained_model_name_or_path=MODEL_PATH,
     torch_dtype=torch.bfloat16,
     device_map="auto",
 )
+processor = AutoProcessor.from_pretrained(MODEL_PATH, use_fast=True)
+
 inputs = processor.apply_chat_template(
     messages,
     tokenize=True,

config.json

@@ -22,7 +22,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 13696,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 65536,
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_key_value_heads": 2,

tokenizer_config.json

@@ -134,7 +134,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
      "151346": {
       "content": "</think>",
@@ -142,7 +142,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
      "151347": {
       "content": "<answer>",
@@ -150,7 +150,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
      "151348": {
       "content": "</answer>",
@@ -158,7 +158,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151349": {
       "content": "<|begin_of_box|>",
@@ -166,7 +166,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151350": {
       "content": "<|end_of_box|>",
@@ -174,7 +174,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151351": {
       "content": "<|sep|>",
@@ -182,7 +182,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
   "additional_special_tokens": [
@@ -200,15 +200,8 @@
     "<|end_of_image|>",
     "<|begin_of_video|>",
     "<|end_of_video|>",
-    "<|begin_of_box|>",
-    "<|end_of_box|>",
-    "<|sep|>",
     "<|image|>",
-    "<|video|>",
-    "<think>",
-    "</think>",
-    "<answer>",
-    "</answer>"
+    "<|video|>"
   ],
   "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
@@ -218,7 +211,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 64000,
+  "model_max_length": 65536,
   "padding_side": "left",
   "remove_space": false,
   "tokenizer_class": "PreTrainedTokenizer"