Update README.md

README.md

@@ -1,21 +1,21 @@
----
-library_name: transformers
-license: mit
-base_model: microsoft/MiniLM-L12-H384-uncased
-tags:
-- generated_from_trainer
-- extractive_QA
-model-index:
-- name: bert-mini-squadv2
-  results: []
-datasets:
-- hf-tuner/squad_v2.0.1
-language:
-- en
-metrics:
-- exact_match
-pipeline_tag: question-answering
----
+---
+library_name: transformers
+license: mit
+base_model: microsoft/MiniLM-L12-H384-uncased
+tags:
+- generated_from_trainer
+- extractive_QA
+model-index:
+- name: bert-mini-squadv2
+  results: []
+datasets:
+- hf-tuner/squad_v2.0.1
+language:
+- en
+metrics:
+- exact_match
+pipeline_tag: question-answering
+---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
@@ -31,6 +31,54 @@ It achieves the following results on the evaluation set:
 
 MiniLMv1-L12-H384-uncased: 12-layer, 384-hidden, 12-heads, 33M parameters, 2.7x faster than BERT-Base
 
+## How to use
+
+```python
+import torch
+from transformers import BertForQuestionAnswering, AutoTokenizer
+
+model_id='hf-tuner/bert-mini-squadv2'
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+bert_qa = BertForQuestionAnswering.from_pretrained(model_id).to(device)
+bert_qa = bert_qa.half()
+
+def get_answers(ctxq):
+  inputs = tokenizer(ctxq, padding=True, return_tensors='pt')
+  for k,v in inputs.items():
+    inputs[k] = v.to(device)
+
+  with torch.no_grad():
+    outputs = bert_qa(**inputs)
+
+  start_idxs = outputs.start_logits.argmax(dim=-1)
+  end_idxs = outputs.end_logits.argmax(dim=-1)
+
+  predictions = []
+  for i, (start_idx, end_idx) in enumerate(zip(start_idxs, end_idxs)):
+    if start_idx == end_idx:
+      predictions.append("<no_answer>")
+    else:
+      predict_answer_tokens = inputs['input_ids'][i, start_idx : end_idx]
+      pred_answer = tokenizer.decode(predict_answer_tokens)
+      predictions.append(pred_answer)
+  return predictions
+
+
+context = """In Q3 2024, xAI raised $6 billion in a Series C round led by Valor Equity Partners and Andreessen Horowitz, with participation from Sequoia Capital, Fidelity, and Saudi Arabia’s Kingdom Holding Company, bringing its post-money valuation to $50 billion.
+"""
+question_1 = "Which two investors co-led xAI’s $6 billion Series C round announced in Q3 2024?"
+question_2 = "On what exact date in Q3 2024 was xAI’s $6 billion Series C funding round officially closed?"
+
+get_answers([
+    [context, question_1],
+    [context, question_2],
+])
+
+>>> ['valor equity partners and andreessen horowitz', '<no_answer>']
+
+```
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: