stefan-it commited on
Commit
d76d731
1 Parent(s): ae1133d

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

Browse files
Files changed (3) hide show
  1. config.json +13 -6
  2. flax_model.msgpack +2 -2
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,21 +1,25 @@
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
- "attn_pdrop": 0.1,
7
- "bos_token_id": 52000,
8
- "embd_pdrop": 0.1,
9
- "eos_token_id": 52000,
 
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
13
  "n_ctx": 1024,
14
  "n_embd": 768,
15
  "n_head": 12,
 
16
  "n_layer": 12,
17
  "n_positions": 1024,
18
- "resid_pdrop": 0.1,
 
19
  "summary_activation": null,
20
  "summary_first_dropout": 0.1,
21
  "summary_proj_to_labels": true,
@@ -27,5 +31,8 @@
27
  "max_length": 50
28
  }
29
  },
30
- "vocab_size": 52000
 
 
 
31
  }
 
1
  {
2
+ "_name_or_path": "./",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
  "initializer_range": 0.02,
13
  "layer_norm_epsilon": 1e-05,
14
  "model_type": "gpt2",
15
  "n_ctx": 1024,
16
  "n_embd": 768,
17
  "n_head": 12,
18
+ "n_inner": null,
19
  "n_layer": 12,
20
  "n_positions": 1024,
21
+ "resid_pdrop": 0.0,
22
+ "scale_attn_weights": true,
23
  "summary_activation": null,
24
  "summary_first_dropout": 0.1,
25
  "summary_proj_to_labels": true,
 
31
  "max_length": 50
32
  }
33
  },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.10.0.dev0",
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
  }
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d7310e0cccc5de05e9a31f541b559be80994f0918f6a9047a88eb6663bb0ab1
3
- size 503118616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e436c321647a102f787ae270289a9afe701c7149ccc95fc6569e15be76f9e30a
3
+ size 497788696
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:634c1d967dc2ac60a1c5abe488615966ea70f7fa03937e107407e1bcf1112edd
3
- size 675497284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3831e1a426b431acdb930bbba251d6595b4ef4d2a7c903db0a60f85a92ab070a
3
+ size 510428686