Upload 8 files

added_tokens.json

@@ -1 +1,3 @@
-{"<|endoftext|>": 50261, "<SECOND_SPEAKER>": 50260, "[FIRST]": 50257, "<FIRST_SPEAKER>": 50259, "[SECOND]": 50258}
+{
+  "<|endoftext|>": 50257
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/media/denis/d9b5b2ab-3dc3-4627-9f99-1ed59b84b83e/polygon/dialog_processor_v11_ruroberta_ranker/tmp/rugpt_neformal_chitchat",
+  "_name_or_path": "/media/denis/d9b5b2ab-3dc3-4627-9f99-1ed59b84b83e/models/rugpt3_medium",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -38,5 +38,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.23.1",
   "use_cache": true,
-  "vocab_size": 50261
+  "vocab_size": 50257
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ Ð
 Ð ¾
 Ð µ

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7f43982b37c183bb4af6f7572807a9fe9c3cbde0c5dd7042dda91cc8d63de1
+oid sha256:e5809cc7067d1e203d78d31b95ea0b7227f1bc056432feaa6512703fcbef4ac2
 size 1524258649

special_tokens_map.json

@@ -1 +1,12 @@
-{"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}, "pad_token": "<pad>"}
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1 +1,33 @@
-{"errors": "replace", "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, "special_tokens_map_file": null, "use_fast": true, "tokenizer_class": "GPT2Tokenizer"}
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "name_or_path": "/media/denis/d9b5b2ab-3dc3-4627-9f99-1ed59b84b83e/models/rugpt3_medium",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}