small and updated version of the model: 125mln parameters, extended dataset

README.md

@@ -16,7 +16,7 @@ widget:
 
 ## Russian Chit-chat with common sence reasoning
 
-Модель является ядром прототипа [диалоговой системы](https://github.com/Koziev/chatbot). У нее есть 2 основные функции.
+Модель является ядром прототипа [диалоговой системы](https://github.com/Koziev/chatbot) с двумя основными функциями.
 
 Первая функция - генерация реплик чит-чата. В качестве затравки подается история диалога (предшествующие несколько реплик, до 10).
 

added_tokens.json

@@ -1 +1,3 @@
-{"<|endoftext|>": 50257}
+{
+  "<|endoftext|>": 50257
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
+  "_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,24 +8,16 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 2048,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 12,
   "n_positions": 2048,
-  "n_special": 0,
-  "output_past": true,
-  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -36,7 +28,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.19.4",
+  "transformers_version": "4.21.3",
   "use_cache": true,
   "vocab_size": 50258
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eafb5c210ea5fef7c9ffebd0c98d6053e1d8795ebae117d7ba41efd98bbedb44
-size 1524262745
+oid sha256:98ae88bfbed22ba3fb913bec46ae4a206825bf67b240af7057f88315a3090b90
+size 551296803

special_tokens_map.json

@@ -1 +1,12 @@
-{"bos_token": "<s>", "eos_token": "</s>", "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 @@
-{"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, "name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2", "errors": "replace", "pad_token": null, "add_bos_token": false, "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": "sberbank-ai/rugpt3small_based_on_gpt2",
+  "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
+  }
+}