c-my/transformers
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
595 Commits 171 Branches 49 Tags
d1e4fa98a91dfebfd88ef77b5ee761665ea0fe4a
Commit Graph
595 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
thomwolf fea15cc9f5 update model conversion 2019-01-16 11:54:54 +01:00
thomwolf a28dfc8659 fix eval for wt103 2019-01-16 11:18:19 +01:00
thomwolf c03c12687f fix __main__ entry script 2019-01-16 10:55:22 +01:00
thomwolf 8831c68803 fixing various parts of model conversion, loading and weights sharing 2019-01-16 10:31:16 +01:00
thomwolf bcd4aa8fe0 update evaluation example 2019-01-15 23:32:34 +01:00
thomwolf a69ec2c722 improved corpus and tokenization conversion - added evaluation script 2019-01-15 23:17:46 +01:00
thomwolf 7d03c53718 conversion working 2019-01-15 16:07:25 +01:00
thomwolf 3a9c88377f adding Transformer XL 2019-01-15 12:59:38 +01:00
Thomas Wolf 647c983530 Merge pull request #193 from nhatchan/20190113_global_step 
Fix importing unofficial TF models
 2019-01-14 09:44:01 +01:00
Thomas Wolf 4e0cba1053 Merge pull request #191 from nhatchan/20190113_py35_finetune 
lm_finetuning compatibility with Python 3.5
 2019-01-14 09:40:07 +01:00
Thomas Wolf c94455651e Merge pull request #190 from nhatchan/20190113_finetune_doc 
Fix documentation (missing backslashes)
 2019-01-14 09:39:03 +01:00
Thomas Wolf 25eae7b0ae Merge pull request #189 from donglixp/patch-1 
[bug fix] args.do_lower_case is always True
 2019-01-14 09:38:37 +01:00
nhatchan cd30565aed Fix importing unofficial TF models 
Importing unofficial TF models seems to be working well, at least for me.
This PR resolves #50.
 2019-01-14 13:35:40 +09:00
nhatchan 8edc898f63 Fix documentation (missing backslashes) 
This PR adds missing backslashes in LM Fine-tuning subsection in README.md.
 2019-01-13 21:23:19 +09:00
nhatchan 6c65cb2492 lm_finetuning compatibility with Python 3.5 
dicts are not ordered in Python 3.5 or prior, which is a cause of #175.
This PR replaces one with a list, to keep its order.
 2019-01-13 21:09:13 +09:00
Li Dong a2da2b4109 [bug fix] args.do_lower_case is always True 
The "default=True" makes args.do_lower_case always True.

```python
parser.add_argument("--do_lower_case",
                        default=True,
                        action='store_true')
```
 2019-01-13 19:51:11 +08:00
Thomas Wolf 35becc6d84 Merge pull request #182 from deepset-ai/fix_lowercase_and_saving 
add do_lower_case arg and adjust model saving for lm finetuning.
 2019-01-11 08:50:13 +01:00
tholor 506e5bb0c8 add do_lower_case arg and adjust model saving for lm finetuning. 2019-01-11 08:32:46 +01:00
Thomas Wolf e485829a41 Merge pull request #174 from abeljim/master 
Added Squad 2.0
 2019-01-10 23:40:45 +01:00
Thomas Wolf 7e60205bd3 Merge pull request #179 from likejazz/patch-2 
Fix it to run properly even if without `--do_train` param.
 2019-01-10 23:39:10 +01:00
Sang-Kil Park 64326dccfb Fix it to run properly even if without --do_train param. 
It was modified similar to `run_classifier.py`, and Fixed to run properly even if without `--do_train` param.
 2019-01-10 21:51:39 +09:00
thomwolf e5c78c6684 update readme and few typos 2019-01-10 01:40:00 +01:00
thomwolf fa5222c296 update readme 2019-01-10 01:25:28 +01:00
Thomas Wolf 0dd5f55ac8 Merge pull request #172 from WrRan/never_split 
Never split some texts.
 2019-01-09 13:44:09 +01:00
Unknown b3628f117e Added Squad 2.0 2019-01-08 15:13:13 -08:00
thomwolf ab90d4cddd adding docs and example for OpenAI GPT 2019-01-09 00:12:43 +01:00
thomwolf dc5df92fa8 added LM head for OpenAI 2019-01-08 17:18:47 +01:00
thomwolf 3cf12b235a added tests + fixed losses 2019-01-08 16:24:23 +01:00
thomwolf eed51c5bdf add OpenAI GPT 2019-01-08 12:26:58 +01:00
WrRan 3f60a60eed text in never_split should not lowercase 2019-01-08 13:33:57 +08:00
WrRan 751beb9e73 never split some text 2019-01-08 10:54:51 +08:00
thomwolf 793dcd236b Merge branch 'master' of https://github.com/huggingface/pytorch-pretrained-BERT into fifth-release 2019-01-07 13:37:55 +01:00
thomwolf 2e4db64cab add do_lower_case tokenizer loading optino in run_squad and ine_tuning examples 2019-01-07 13:06:42 +01:00
thomwolf c9fd350567 remove default when action is store_true in arguments 2019-01-07 13:01:54 +01:00
thomwolf 93f563b8a8 adding OpenAI GPT 2019-01-07 12:55:36 +01:00
Thomas Wolf e048c7f1c8 Merge pull request #171 from donglixp/patch-1 
LayerNorm initialization
 2019-01-07 12:44:46 +01:00
Thomas Wolf d3d56f9a0b Merge pull request #166 from likejazz/patch-1 
Fix error when `bert_model` param is path or url.
 2019-01-07 12:40:55 +01:00
Thomas Wolf 766c6b2ce3 Merge pull request #159 from jaderabbit/master 
Allow do_eval to be used without do_train and to use the pretrained model in the output folder
 2019-01-07 12:31:06 +01:00
Thomas Wolf 77966a43a4 Merge pull request #156 from rodgzilla/cl_args_doc 
Adding new pretrained model to the help of the `bert_model` argument.
 2019-01-07 12:27:16 +01:00
Thomas Wolf bcd607542c Merge pull request #145 from wlhgtc/master 
Correct the  wrong note
 2019-01-07 12:23:05 +01:00
Thomas Wolf 2e8c5c00ec Merge pull request #141 from SinghJasdeep/patch-1 
loading saved model when n_classes != 2
 2019-01-07 12:21:13 +01:00
Thomas Wolf 2860377021 Merge pull request #134 from rodgzilla/update_doc_pretrained_models 
Fixing various class documentations.
 2019-01-07 12:06:06 +01:00
Thomas Wolf c18bdb4433 Merge pull request #124 from deepset-ai/master 
Add example for fine tuning BERT language model
 2019-01-07 12:03:51 +01:00
Li Dong d0d9b384f2 LayerNorm initialization 
The LayerNorm gamma and beta should be initialized by .fill_(1.0) and .zero_().

reference links:

https://github.com/tensorflow/tensorflow/blob/989e78c412a7e0f5361d4d7dfdfb230c8136e749/tensorflow/contrib/layers/python/layers/layers.py#L2298

https://github.com/tensorflow/tensorflow/blob/989e78c412a7e0f5361d4d7dfdfb230c8136e749/tensorflow/contrib/layers/python/layers/layers.py#L2308
 2019-01-07 15:51:33 +08:00
Sang-Kil Park ca4e7aaa72 Fix error when bert_model param is path or url. 
Error occurs when `bert_model` param is path or url. Therefore, if it is path, specify the last path to prevent error.
 2019-01-05 11:42:54 +09:00
Jade Abbott 193e2df8ba Remove rogue comment 2019-01-03 13:13:06 +02:00
Jade Abbott c64de50ea4 nb_tr_steps is not initialized 2019-01-03 12:34:57 +02:00
Jade Abbott b96149a19b Training loss is not initialized if only do_eval is specified 2019-01-03 10:32:10 +02:00
Jade Abbott be3b9bcf4d Allow one to use the pretrained model in evaluation when do_train is not selected 2019-01-03 09:02:33 +02:00
Grégory Châtel 186f75342e Adding new pretrained model to the help of the bert_model argument. 2019-01-02 14:00:59 +01:00