Move to in-library checkpoint

config.json

@@ -2,13 +2,9 @@
   "alibi": true,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "RWForCausalLM"
+    "FalconForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_RW.RWConfig",
-    "AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
-  },
   "bias": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
@@ -16,13 +12,14 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "RefinedWebModel",
+  "model_type": "falcon",
   "multi_query": false,
-  "n_head": 64,
-  "n_layer": 36,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 64,
+  "num_hidden_layers": 36,
   "parallel_attn": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.27.4",
   "use_cache": true,
   "vocab_size": 65024
-}
+}

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.27.4"
-}
+  "transformers_version": "4.31.0.dev0"
+}

tokenizer_config.json

@@ -1,8 +1,12 @@
 {
   "add_prefix_space": false,
   "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "model_max_length": 2048,
   "name_or_path": "guipenedo/dd_alpha",
   "special_tokens_map_file": null,
   "tokenizer_class": "PreTrainedTokenizerFast"
-}
+}