start

README.md

@@ -1,3 +1,71 @@
 ---
-license: mit
+license: apache-2.0
+tags:
+- Question Answering
+metrics:
+- squad
+model-index:
+- name: consciousAI/question-answering-roberta-base-s-v2
+  results: []
 ---
+
+# Question Answering 
+The model is intended to be used for Q&A task, given the question & context, the model would attempt to infer the answer text, answer span & confidence score.<br>
+Model is encoder-only (deepset/roberta-base-squad2) with QuestionAnswering LM Head, fine-tuned on SQUADx dataset with **exact_match:** 84.83 & **f1:** 91.80 performance scores.
+
+[Live Demo: Question Answering Encoders vs Generative](https://huggingface.co/spaces/consciousAI/question_answering)
+
+Please follow this link for [Encoder based Question Answering V1](https://huggingface.co/consciousAI/question-answering-roberta-base-s/)
+<br>Please follow this link for [Generative Question Answering](https://huggingface.co/consciousAI/question-answering-generative-t5-v1-base-s-q-c/)
+
+Example code:
+```
+from transformers import pipeline
+
+model_checkpoint = "consciousAI/question-answering-roberta-base-s-v2"
+
+context = """
+🤗 Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration
+between them. It's straightforward to train your models with one before loading them for inference with the other.
+"""
+question = "Which deep learning libraries back 🤗 Transformers?"
+
+question_answerer = pipeline("question-answering", model=model_checkpoint)
+question_answerer(question=question, context=context)
+
+```
+
+## Training and evaluation data
+
+SQUAD Split
+
+## Training procedure
+
+Preprocessing:
+1. SQUAD Data longer chunks were sub-chunked with input context max-length 384 tokens and stride as 128 tokens.
+2. Target answers readjusted for sub-chunks, sub-chunks with no-answers or partial answers were set to target answer span as (0,0)
+
+Metrics:
+1. Adjusted accordingly to handle sub-chunking.
+2. n best = 20
+3. skip answers with length zero or higher than max answer length (30)
+
+### Training hyperparameters
+Custom Training Loop:
+The following hyperparameters were used during training:
+- learning_rate: 2e-5
+- train_batch_size: 32
+- eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+{'exact_match': 84.83443708609272, 'f1': 91.79987545811638}
+
+### Framework versions
+
+- Transformers 4.23.0.dev0
+- Pytorch 1.12.1+cu113
+- Datasets 2.5.2
+- Tokenizers 0.13.0

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepset/roberta-base-squad2",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "name": "Roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee236622f4779221a5756b867a9c00ebeab8a899df9678eecb8390684efbf34
+size 496254452

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c224e441eccb753f528424054215d608ef5bf4e8a60ecb32923d23e6ce9b869d
+size 496297393

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "deepset/roberta-base-squad2",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--deepset--roberta-base-squad2/snapshots/e888b4b0bc8ccea2aff7828002f821047c246114/special_tokens_map.json",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}