update for new format config of transformers lib / sglang lib

config.json

@@ -3,15 +3,16 @@
     "Glm4vMoeForConditionalGeneration"
   ],
   "model_type": "glm4v_moe",
-  "rope_scaling": {
-    "rope_type": "default",
-    "mrope_section": [
-      8,
-      12,
-      12
-    ]
-  },
+  "image_start_token_id": 151339,
+  "image_end_token_id": 151340,
+  "video_start_token_id": 151341,
+  "video_end_token_id": 151342,
+  "image_token_id": 151363,
+  "video_token_id": 151364,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
   "text_config": {
+    "model_type": "glm4v_moe_text",
     "pad_token_id": 151329,
     "vocab_size": 151552,
     "eos_token_id": [
@@ -19,9 +20,6 @@
       151336,
       151338
     ],
-    "image_end_token_id": 151340,
-    "image_start_token_id": 151339,
-    "image_token_id": 151363,
     "head_dim": 128,
     "attention_bias": true,
     "attention_dropout": 0.0,
@@ -31,7 +29,6 @@
     "initializer_range": 0.02,
     "intermediate_size": 10944,
     "max_position_embeddings": 65536,
-    "model_type": "glm4v_moe_text",
     "moe_intermediate_size": 1408,
     "n_group": 1,
     "n_routed_experts": 128,
@@ -43,7 +40,7 @@
     "num_key_value_heads": 8,
     "partial_rotary_factor": 0.5,
     "rms_norm_eps": 1e-05,
-    "torch_dtype": "bfloat16",
+    "dtype": "bfloat16",
     "rope_scaling": {
       "rope_type": "default",
       "mrope_section": [
@@ -58,11 +55,6 @@
     "use_cache": true,
     "use_qk_norm": false
   },
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.0.dev0",
-  "video_end_token_id": 151342,
-  "video_start_token_id": 151341,
-  "video_token_id": 151364,
   "vision_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 1.0,
   "top_k": 1,
   "top_p": 0.0001,
-  "transformers_version": "4.55.0.dev"
+  "transformers_version": "4.57.1"
 }