From deedc3e42208524e0df3d9149d1f26aa6934f05f Mon Sep 17 00:00:00 2001 From: Branden Chan Date: Wed, 11 Nov 2020 14:53:33 +0100 Subject: [PATCH] Update to v2 --- README.md | 120 ++++++++++++++++++++++++++++++++++++++++ config.json | 2 +- pytorch_model.bin | 4 +- special_tokens_map.json | 2 +- tokenizer_config.json | 2 +- 5 files changed, 125 insertions(+), 5 deletions(-) create mode 100644 README.md diff --git a/README.md b/README.md new file mode 100644 index 0000000..c792cf2 --- /dev/null +++ b/README.md @@ -0,0 +1,120 @@ +--- +datasets: +- squad_v2 +--- + +# roberta-base for QA + +NOTE: This is version 2 of the model. See [this github issue](https://github.com/deepset-ai/FARM/issues/552) from the FARM repository for an explanation of why we updated. + +## Overview +**Language model:** roberta-base +**Language:** English +**Downstream-task:** Extractive QA +**Training data:** SQuAD 2.0 +**Eval data:** SQuAD 2.0 +**Code:** See [example](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py) in [FARM](https://github.com/deepset-ai/FARM/blob/master/examples/question_answering.py) +**Infrastructure**: 4x Tesla v100 + +## Hyperparameters + +``` +batch_size = 96 +n_epochs = 2 +base_LM_model = "roberta-base" +max_seq_len = 386 +learning_rate = 3e-5 +lr_schedule = LinearWarmup +warmup_proportion = 0.2 +doc_stride=128 +max_query_length=64 +``` + +## Performance +Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/). + +``` +"exact": 79.97136359807968 +"f1": 83.00449234495325 + +"total": 11873 +"HasAns_exact": 78.03643724696356 +"HasAns_f1": 84.11139298441825 +"HasAns_total": 5928 +"NoAns_exact": 81.90075693860386 +"NoAns_f1": 81.90075693860386 +"NoAns_total": 5945 +``` + +## Usage + +### In Transformers +```python +from transformers.pipelines import pipeline +from transformers.modeling_auto import AutoModelForQuestionAnswering +from transformers.tokenization_auto import AutoTokenizer + +model_name = "deepset/roberta-base-squad2-v2" + +# a) Get predictions +nlp = pipeline('question-answering', model=model_name, tokenizer=model_name) +QA_input = { + 'question': 'Why is model conversion important?', + 'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.' +} +res = nlp(QA_input) + +# b) Load model & tokenizer +model = AutoModelForQuestionAnswering.from_pretrained(model_name) +tokenizer = AutoTokenizer.from_pretrained(model_name) +``` + +### In FARM + +```python +from farm.modeling.adaptive_model import AdaptiveModel +from farm.modeling.tokenization import Tokenizer +from farm.infer import Inferencer + +model_name = "deepset/roberta-base-squad2-v2" + +# a) Get predictions +nlp = Inferencer.load(model_name, task_type="question_answering") +QA_input = [{"questions": ["Why is model conversion important?"], + "text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}] +res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True) + +# b) Load model & tokenizer +model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering") +tokenizer = Tokenizer.load(model_name) +``` + +### In haystack +For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in [haystack](https://github.com/deepset-ai/haystack/): +```python +reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2") +# or +reader = TransformersReader(model="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2") +``` + + +## Authors +Branden Chan: `branden.chan [at] deepset.ai` +Timo Möller: `timo.moeller [at] deepset.ai` +Malte Pietsch: `malte.pietsch [at] deepset.ai` +Tanay Soni: `tanay.soni [at] deepset.ai` + +## About us +![deepset logo](https://raw.githubusercontent.com/deepset-ai/FARM/master/docs/img/deepset_logo.png) + +We bring NLP to the industry via open source! +Our focus: Industry specific language models & large scale QA systems. + +Some of our work: +- [German BERT (aka "bert-base-german-cased")](https://deepset.ai/german-bert) +- [FARM](https://github.com/deepset-ai/FARM) +- [Haystack](https://github.com/deepset-ai/haystack/) + +Get in touch: +[Twitter](https://twitter.com/deepset_ai) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Website](https://deepset.ai) + diff --git a/config.json b/config.json index fa0c801..a1f66a8 100644 --- a/config.json +++ b/config.json @@ -5,6 +5,7 @@ "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, + "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, @@ -17,7 +18,6 @@ "name": "Roberta", "num_attention_heads": 12, "num_hidden_layers": 12, - "output_past": true, "pad_token_id": 1, "type_vocab_size": 1, "vocab_size": 50265 diff --git a/pytorch_model.bin b/pytorch_model.bin index ccba5f4..fe36f7e 100644 --- a/pytorch_model.bin +++ b/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6f38b2e5443a0aa0aab23c665a8c033f00ba9d85424a0f5c1acd8bbdf36df6ef -size 498637366 +oid sha256:e0b64ccefc1bcb569b604baea27eb873e5482fdf6eb3ceff1fb5368397db5aed +size 496313727 diff --git a/special_tokens_map.json b/special_tokens_map.json index 6cd1d90..e97d199 100644 --- a/special_tokens_map.json +++ b/special_tokens_map.json @@ -1 +1 @@ -{"bos_token": "", "eos_token": "", "unk_token": "", "sep_token": "", "pad_token": "", "cls_token": "", "mask_token": ""} \ No newline at end of file +{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json index 32b043b..716c997 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -1 +1 @@ -{"do_lower_case": true, "max_len": 512, "bos_token": "", "eos_token": "", "unk_token": "", "sep_token": "", "pad_token": "", "cls_token": "", "mask_token": ""} \ No newline at end of file +{"do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null}