Update config.json

config.json

@@ -1,15 +1,17 @@
+{
+  "_name_or_path": "sciphi/triplex",
   "architectures": [
-    "sciphi/triplex"
+    "Phi3ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
-    "AutoModel": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
-    "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
   },
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
   "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
@@ -17,6 +19,8 @@
   "model_type": "phi3",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
@@ -121,14 +125,14 @@
       2.8999999999999977,
       3.049999999999997
     ],
-    "type": "yarn"
+      "type": "longrope"
   },
   "rope_theta": 10000.0,
   "sliding_window": 262144,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.3",
-  "use_cache": false,
-
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "attention_bias": false,
   "vocab_size": 32064
-}
+}