Update config.json

config.json

@@ -1,50 +1,45 @@
 {
   "_name_or_path": "THUDM/glm-4-9b-chat",
-  "add_bias_linear": false,
-  "add_qkv_bias": true,
-  "apply_query_key_layer_scaling": true,
-  "apply_residual_connection_post_layernorm": false,
+  "model_type": "chatglm",
   "architectures": [
-    "ChatGLMForConditionalGeneration"
+    "ChatGLMModel"
   ],
-  "attention_dropout": 0.0,
-  "attention_softmax_in_fp32": true,
   "auto_map": {
     "AutoConfig": "configuration_chatglm.ChatGLMConfig",
     "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForCausalLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSequenceClassification": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForSequenceClassification"
+    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
   },
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "attn_implementation": "sdpa",
   "bias_dropout_fusion": true,
-  "classifier_dropout": null,
-  "eos_token_id": [
-    151329,
-    151336,
-    151338
-  ],
   "ffn_hidden_size": 13696,
   "fp32_residual_connection": false,
   "hidden_dropout": 0.0,
   "hidden_size": 4096,
   "kv_channels": 128,
   "layernorm_epsilon": 1.5625e-07,
-  "model_type": "chatglm",
   "multi_query_attention": true,
   "multi_query_group_num": 2,
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_layers": 40,
+  "rope_ratio": 500,
   "original_rope": true,
-  "pad_token_id": 151329,
   "padded_vocab_size": 151552,
   "post_layer_norm": true,
   "rmsnorm": true,
-  "rope_ratio": 500,
   "seq_length": 131072,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 151552
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "tie_word_embeddings": false,
+  "eos_token_id": [151329, 151336, 151338],
+  "pad_token_id": 151329
 }