Commit from colab

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
+  "_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,16 +8,24 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 2048,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 24,
   "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,
@@ -30,5 +38,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.16.2",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1f0d84ef1079701c83ff564124ad358c399a79e64e48787e14b67d35658b4d
-size 551319785
+oid sha256:46c362b75386c0250fcf748cac4880eb9692074c69f0b525494873e359415a50
+size 1524273113

tokenizer_config.json

@@ -1 +1 @@
-{"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/rugpt3small_based_on_gpt2", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
+{"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", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338449769623e92b438a7ed6bbc03986348358994b5a1d22545e14e260da2926
+oid sha256:4a54fb90143bbc04b2dfdbe8cbdcd9ef94eb712cb8d27a668ac2e7ce60b197db
 size 2991