adding files : generation_config.json, special_tokens_map.json, tokenizer.json, tokenizer_config.json

config.json

@@ -0,0 +1,32 @@
+{
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "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,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.27.4"
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "add_prefix_space": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "name_or_path": "tiiuae/falcon_tokenizer",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}