MiriUll commited on
Commit
b7ddf41
1 Parent(s): 8312780

Upload 9 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|BOS|>": 50258,
3
+ "<|EOS|>": 50257,
4
+ "<|pad|>": 50259
5
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ml6team/gpt2-medium-german-finetune-oscar",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50258,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50257,
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": 1024,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 1024,
21
+ "n_special": 0,
22
+ "pad_token_id": 50259,
23
+ "predict_special_tokens": true,
24
+ "reorder_and_upcast_attn": false,
25
+ "resid_pdrop": 0.1,
26
+ "scale_attn_by_inverse_layer_idx": false,
27
+ "scale_attn_weights": true,
28
+ "summary_activation": null,
29
+ "summary_first_dropout": 0.1,
30
+ "summary_proj_to_labels": true,
31
+ "summary_type": "cls_index",
32
+ "summary_use_proj": true,
33
+ "task_specific_params": {
34
+ "text-generation": {
35
+ "do_sample": true,
36
+ "max_length": 50
37
+ }
38
+ },
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.25.1",
41
+ "use_cache": true,
42
+ "vocab_size": 50260
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591a210d3aaeb4d9075264a799fb9d506a4cfe5c6cfba4d54b3d53401f225339
3
+ size 1444579161
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|BOS|>",
3
+ "eos_token": "<|EOS|>",
4
+ "pad_token": "<|pad|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "full_tokenizer_file": null,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "name_or_path": "ml6team/gpt2-medium-german-finetune-oscar",
24
+ "pad_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "special_tokens_map_file": null,
33
+ "tokenizer_class": "GPT2Tokenizer",
34
+ "unk_token": {
35
+ "__type": "AddedToken",
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64518f3646ee21322c1342b300caea90a35b73474f631798de48a658dfb98a5
3
+ size 3567
vocab.json ADDED
The diff for this file is too large to render. See raw diff