Update config.json

config.json

@@ -3,16 +3,16 @@
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "FalconForCausalLM"
+    "RWForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
-    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
+    "AutoConfig": "configuration_RW.RWConfig",
+    "AutoModel": "modelling_RW.RWModel",
+    "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification",
+    "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
+    "AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
   },
   "bias": false,
   "bos_token_id": 11,
@@ -21,15 +21,13 @@
   "hidden_size": 4544,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "falcon",
+  "model_type": "RefinedWebModel",
   "multi_query": true,
-  "new_decoder_architecture": false,
-  "num_attention_heads": 71,
-  "num_hidden_layers": 32,
-  "num_kv_heads": 71,
+  "n_head": 71,
+  "n_layer": 32,
   "parallel_attn": true,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.30.0",
   "use_cache": true,
   "vocab_size": 65024
-}
+}