Update config.json

config.json

@@ -1,26 +1,29 @@
 {
-  "_name_or_path": "/data//ldwang/state_dict/Aquila-7b-knowledge5-ep2-110973-v910-ep1-knowledge62-214000-megatron-hf",
   "architectures": [
-    "LlamaForCausalLM"
+    "AquilaForCausalLM"
   ],
+  "auto_map": {
+    "AutoConfig": "configuration_aquila.AquilaConfig",
+    "AutoModelForCausalLM": "modeling_aquila.AquilaForCausalLM"
+  },
   "bos_token_id": 100006,
   "eos_token_id": 100007,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 6144,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 2048,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 4096,
+  "model_type": "aquila",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 100008
-}
+}