Update config.json

config.json

@@ -1,28 +1,20 @@
 {
   "architectures": [
-    "MiniMindLM"
+    "Transformer"
   ],
-  "aux_loss_alpha": 0.1,
-  "dim": 512,
-  "dropout": 0.0,
-  "flash_attn": true,
-  "hidden_dim": 1408,
-  "max_seq_len": 512,
   "model_type": "minimind",
-  "multiple_of": 64,
-  "n_heads": 8,
-  "n_kv_heads": 2,
-  "n_layers": 8,
-  "n_routed_experts": 4,
-  "n_shared_experts": true,
-  "norm_eps": 1e-05,
-  "norm_topk_prob": true,
-  "num_experts_per_tok": 2,
-  "rope_theta": 1000000.0,
-  "scoring_func": "softmax",
-  "seq_aux": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
-  "use_moe": false,
-  "vocab_size": 6400
+  "hidden_size": 512,
+  "num_hidden_layers": 8,
+  "num_attention_heads": 16,
+  "vocab_size": 6400,
+  "max_position_embeddings": 512,
+  "intermediate_size": 2048,
+  "hidden_dropout_prob": 0.0,
+  "attention_probs_dropout_prob": 0.0,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "use_cache": true
 }