w11wo commited on
Commit
4343083
1 Parent(s): 9af8360

8 epochs of training

Browse files
.gitattributes CHANGED
@@ -16,3 +16,4 @@
16
  *.pth filter=lfs diff=lfs merge=lfs -text
17
  *tfevents* filter=lfs diff=lfs merge=lfs -text
18
  nohup.out filter=lfs diff=lfs merge=lfs -text
 
 
16
  *.pth filter=lfs diff=lfs merge=lfs -text
17
  *tfevents* filter=lfs diff=lfs merge=lfs -text
18
  nohup.out filter=lfs diff=lfs merge=lfs -text
19
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "RobertaForMaskedLM"
4
  ],
@@ -18,6 +19,7 @@
18
  "num_hidden_layers": 12,
19
  "pad_token_id": 1,
20
  "position_embedding_type": "absolute",
 
21
  "transformers_version": "4.9.0.dev0",
22
  "type_vocab_size": 1,
23
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "./",
3
  "architectures": [
4
  "RobertaForMaskedLM"
5
  ],
 
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
  "transformers_version": "4.9.0.dev0",
24
  "type_vocab_size": 1,
25
  "use_cache": true,
flax_to_torch.py ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ from transformers import RobertaForMaskedLM, AutoTokenizer
2
+
3
+ model = RobertaForMaskedLM.from_pretrained("./", from_flax=True)
4
+ model.save_pretrained("./")
5
+
6
+ tokenizer = AutoTokenizer.from_pretrained("./")
7
+ tokenizer.save_pretrained("./")
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
nohup.out CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9c9571bb69f151d306a7ad2f06eef318d7029e1e59af5690b0f70956f372972
3
- size 16226324
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9fffea38d0dacea94cfb0e33cf554ebdbaeff9521b45dbcb37d812928152ca
3
+ size 16228479
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:843ba5529934bfa14c528bb50647d74e9836326d686510660c2836e15a218ed2
3
+ size 498858859
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff