model: prepare release of re-trained German GPT-2 model

config.json

@@ -1,21 +1,25 @@
 {
+  "_name_or_path": "./",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 52000,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 52000,
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
+  "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "resid_pdrop": 0.1,
+  "resid_pdrop": 0.0,
+  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -27,5 +31,8 @@
       "max_length": 50
     }
   },
-  "vocab_size": 52000
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
 }

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7310e0cccc5de05e9a31f541b559be80994f0918f6a9047a88eb6663bb0ab1
-size 503118616
+oid sha256:e436c321647a102f787ae270289a9afe701c7149ccc95fc6569e15be76f9e30a
+size 497788696

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634c1d967dc2ac60a1c5abe488615966ea70f7fa03937e107407e1bcf1112edd
-size 675497284
+oid sha256:3831e1a426b431acdb930bbba251d6595b4ef4d2a7c903db0a60f85a92ab070a
+size 510428686