change files

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "MiniMaxText01ForCausalLM"
+    "AbabForCausalLM"
   ],
   "attention_dropout": 0.0,
   "attn_type_list": [
@@ -86,24 +86,21 @@
     1
   ],
   "auto_map": {
-    "AutoConfig": "configuration_minimax_text_01.MiniMaxText01Config",
-    "AutoModelForCausalLM": "modeling_minimax_text_01.MiniMaxText01ForCausalLM"
+    "AutoConfig": "configuration_abab.AbabConfig",
+    "AutoModelForCausalLM": "modeling_abab.AbabForCausalLM"
   },
-  "bos_token_id": null,
-  "eos_token_id": null,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 6144,
   "initializer_range": 0.02,
   "intermediate_size": 9216,
   "layernorm_full_attention_alpha": 3.5565588200778455,
-  "layernorm_full_attention_beta": 1.0,
   "layernorm_linear_attention_alpha": 3.5565588200778455,
-  "layernorm_linear_attention_beta": 1.0,
   "layernorm_mlp_alpha": 3.5565588200778455,
-  "layernorm_mlp_beta": 1.0,
-  "max_position_embeddings": 10240000,
-  "model_type": "minimax_text_01",
+  "max_position_embeddings": 131072,
+  "model_type": "mixtral",
   "num_attention_heads": 64,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 80,
@@ -120,7 +117,7 @@
   "shared_moe_mode": "sigmoid",
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.49.0",
   "use_cache": true,
   "vocab_size": 200064
 }