revert changes

config.json

@@ -3,16 +3,16 @@
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "FalconForCausalLM"
+    "RWForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_falcon.FalconConfig",
-    "AutoModel": "modeling_falcon.FalconModel",
-    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
-    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
+    "AutoConfig": "tiiuae/falcon-40b--configuration_RW.RWConfig",
+    "AutoModel": "tiiuae/falcon-40b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-40b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-40b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-40b--modelling_RW.RWForTokenClassification"
   },
   "bias": false,
   "bos_token_id": 11,
@@ -21,14 +21,13 @@
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "falcon",
-  "new_decoder_architecture": true,
-  "num_attention_heads": 128,
-  "num_hidden_layers": 60,
-  "num_kv_heads": 8,
+  "model_type": "RefinedWeb",
+  "n_head": 128,
+  "n_head_kv": 8,
+  "n_layer": 60,
   "parallel_attn": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.30.1",
   "use_cache": true,
   "vocab_size": 65024
-}
+}