synchronizing config.json (official HF support)

config.json

@@ -1,14 +1,17 @@
 {
-  "_name_or_path": "tiiuae/falcon-7b-instruct",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "RWForCausalLM"
+    "FalconForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--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,
@@ -17,13 +20,14 @@
   "hidden_size": 4544,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "RefinedWebModel",
+  "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": "float32",
-  "transformers_version": "4.31.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.4",
   "use_cache": true,
   "vocab_size": 65024
 }