Convert to in-library checkpoint

config.json

@@ -2,17 +2,9 @@
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "RWForCausalLM"
+    "FalconForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "auto_map": {
-    "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,
   "eos_token_id": 11,
@@ -20,13 +12,14 @@
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "RefinedWeb",
-  "n_head": 128,
-  "n_head_kv": 8,
-  "n_layer": 60,
+  "model_type": "falcon",
+  "new_decoder_architecture": true,
+  "num_attention_heads": 128,
+  "num_hidden_layers": 60,
+  "num_kv_heads": 8,
   "parallel_attn": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.27.4",
   "use_cache": true,
   "vocab_size": 65024
-}
+}

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.27.4"
-}
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.31.0.dev0"
+}

tokenizer_config.json

@@ -1,7 +1,11 @@
 {
   "add_prefix_space": false,
   "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "model_max_length": 2048,
   "special_tokens_map_file": null,
   "tokenizer_class": "PreTrainedTokenizerFast"
-}
+}