tokenizer update

added_tokens.json

@@ -1 +1 @@
-{"<|sep|>": 50257, "<|cls|>": 50258, "<|start|>": 50259, "<|p1|>": 50260, "<|p2|>": 50261}
+{"<|sep|>": 50257, "<|act|>": 50262, "<|cls|>": 50258, "<|start|>": 50259, "<|p1|>": 50260, "<|p2|>": 50261}

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "af1tang/personaGPT",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -7,19 +8,25 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 1024,
   "n_head": 16,
+  "n_inner": null,
   "n_layer": 24,
   "n_positions": 1024,
   "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "vocab_size": 50262
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50263
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7582d23d2d19e37339c15685b171dce5e6ea98787a82b40ff3c4ad8011a87a6
-size 1444551925
+oid sha256:7397c2e647a7d4e328b67f4d5cac13cb32713a6282a94e41db2ed44782aad2e3
+size 1444556021

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": "<|sep|>", "pad_token": "<|endoftext|>", "cls_token": "<|cls|>", "additional_special_tokens": ["<|start|>", "<|p1|>", "<|p2|>"]}
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": "<|sep|>", "pad_token": "<|endoftext|>", "cls_token": "<|cls|>", "additional_special_tokens": ["<|start|>", "<|p1|>", "<|p2|>", "<|act|>"]}

tokenizer_config.json

@@ -1 +1 @@
-{"pad_token": "<|endoftext|>", "cls_token": "<|cls|>", "sep_token": "<|sep|>", "special_tokens_map_file": null, "full_tokenizer_file": null}
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "pad_token": "<|endoftext|>", "cls_token": "<|cls|>", "sep_token": "<|sep|>", "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "af1tang/personaGPT", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}