Update config.json

config.json

@@ -2,15 +2,17 @@
   "_name_or_path": "tiiuae/falcon-7b",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
-  "architectures": ["RWForCausalLM"],
+  "architectures": [
+    "FalconForCausalLM"
+  ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_RW.RWConfig",
-    "AutoModel": "modelling_RW.RWModel",
-    "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
-    "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification",
-    "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
-    "AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
+    "AutoConfig": "configuration_falcon.FalconConfig",
+    "AutoModel": "modeling_falcon.FalconModel",
+    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
+    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
   },
   "bias": false,
   "bos_token_id": 11,
@@ -18,14 +20,15 @@
   "hidden_dropout": 0.0,
   "hidden_size": 4544,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-5,
-  "model_type": "RefinedWebModel",
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "falcon",
   "multi_query": true,
-  "n_head": 71,
-  "n_layer": 32,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
   "parallel_attn": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.30.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.4",
   "use_cache": true,
   "vocab_size": 65024
 }