Upload config

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
@@ -6,12 +7,12 @@
   ],
   "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": "vilsonrodrigues/falcon-7b-instruct-sharded--configuration_falcon.FalconConfig",
+    "AutoModel": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForTokenClassification"
   },
   "bias": false,
   "bos_token_id": 11,
@@ -25,9 +26,10 @@
   "new_decoder_architecture": false,
   "num_attention_heads": 71,
   "num_hidden_layers": 32,
+  "num_kv_heads": 71,
   "parallel_attn": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.30.0.dev0",
   "use_cache": true,
   "vocab_size": 65024
-}
+}