First model version_15

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "sberbank-ai/rugpt2large",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,20 +9,31 @@
   "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_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 2048,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "output_past": true,
   "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": 50264
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 50257
 }

flax_model.msgpack

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:322182be41c143f2f8ecd8b9e76018d09ae5ca4c752b8858a257811bb4c5f5da
-size 500931352

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2a4a387b0430654bb1f6813436bd31f8e10a06e18ea0e5c41b33120b78458e
-size 551290714
+oid sha256:18c57ed38e675907191e0caba58e83af0dcd6ffd3849d512495d9ef73e6b32fe
+size 3134058823

special_tokens_map.json

@@ -0,0 +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}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"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, "tokenizer_file": null, "name_or_path": "sberbank-ai/rugpt2large", "tokenizer_class": "GPT2Tokenizer"}