Update README.md

README.md

@@ -51,6 +51,36 @@ for i in range(len(sample_outputs)):
 
         
         
+# to select the top n results:
+
+from transformers import AutoTokenizer, AutoModelWithLMHead
+tokenizer = AutoTokenizer.from_pretrained("salesken/clariq_gpt2")
+model = AutoModelWithLMHead.from_pretrained("salesken/clariq_gpt2") 
+
+
+
+input_query="Serve your models directly from Hugging Face infrastructure and run large scale NLP models in milliseconds with just a few lines of code"
+
+query= input_query + " ~~ "
+
+
+input_ids = tokenizer.encode(query.lower(), return_tensors='pt')
+sample_outputs = model.generate(input_ids,
+                                do_sample=True,
+                                num_beams=1, 
+                                max_length=128,
+                                temperature=0.9,
+                                top_k = 40,
+                                num_return_sequences=10)
+clarifications_gen = []
+for i in range(len(sample_outputs)):
+    r = tokenizer.decode(sample_outputs[i], skip_special_tokens=True).split('||')[0]
+    r = r.split(' ~~ ~~')[1]
+    if r not in clarifications_gen:
+        clarifications_gen.append(r)
+
+print(clarifications_gen)
+
 # to select the top n results:
 
 from sentence_transformers import SentenceTransformer, util
@@ -63,8 +93,9 @@ corpus_embeddings = embedder.encode(corpus, convert_to_tensor=True)
 query = input_query.lower()
 query_embedding = embedder.encode(query, convert_to_tensor=True)
 cos_scores = util.pytorch_cos_sim(query_embedding, corpus_embeddings)[0]
-top_results = torch.topk(cos_scores, k=1)
-for score, idx in zip(top_results[0], top_results[3]):
+top_results = torch.topk(cos_scores, k=5)
+print("Top clarifications generated :")
+for score, idx in zip(top_results[0], top_results[1]):
     print(corpus[idx], "(Score: {:.4f})".format(score))
 
 ```