birgermoell
commited on
Commit
•
a27c158
1
Parent(s):
3aeea40
Updated pytorch model export
Browse files- exported_pytorch_model/config.json +27 -0
- exported_pytorch_model/merges.txt +0 -0
- exported_pytorch_model/pytorch_model.bin +3 -0
- exported_pytorch_model/special_tokens_map.json +1 -0
- exported_pytorch_model/tokenizer.json +0 -0
- exported_pytorch_model/tokenizer_config.json +1 -0
- exported_pytorch_model/vocab.json +0 -0
- save_updated.py +6 -0
exported_pytorch_model/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": ".",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
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,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
exported_pytorch_model/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
exported_pytorch_model/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea3fa1dcdc98e0f6702ebc4dec5962555ad413f2a9795de69371106dfb806a8a
|
3 |
+
size 498661169
|
exported_pytorch_model/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}}
|
exported_pytorch_model/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
exported_pytorch_model/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"}
|
exported_pytorch_model/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
save_updated.py
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
from transformers import AutoTokenizer, RobertaModel
|
3 |
+
model = RobertaModel.from_pretrained('.',from_flax=True)
|
4 |
+
tokenizer = AutoTokenizer.from_pretrained(".")
|
5 |
+
tokenizer.save_pretrained('exported_pytorch_model')
|
6 |
+
model.save_pretrained('exported_pytorch_model')
|