Update config.json

config.json

@@ -1,10 +1,19 @@
 {
+  "_name_or_path": "tiiuae/falcon-7b",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "RWForCausalL"
+    "FalconForCausalLM"
   ],
   "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"
+  },
   "bias": false,
   "bos_token_id": 11,
   "eos_token_id": 11,
@@ -12,13 +21,18 @@
   "hidden_size": 4544,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
   "multi_query": true,
-  "n_head": 71,
-  "n_layer": 32,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
   "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.34.0.dev0",
   "use_cache": true,
-  "vocab_size": 65024,
-  "model_type": "falcon"
-}
+  "vocab_size": 65024
+}