803847b9eae6a8d935423a5acddc79fea9e3a3c1cbeb92942fc8f17d8b6fcb36

config.json

@@ -4,6 +4,7 @@
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -27,14 +28,15 @@
     "model_version": 1,
     "outlier_channel_split": false,
     "packsz": 4,
-    "rescale_WH": false
+    "rescale_WH": false,
+    "resid_scale_override": -1
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.36.2",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.36.2"
 }