Upload folder using huggingface_hub

README.md

@@ -1778,11 +1778,29 @@ def last_token_pool(last_hidden_states: Tensor,
 
 
 def get_detailed_instruct(task_description: str, query: str) -> str:
-    return f'<instruct>{task_description}\n<query>{query}\n<response>'
+    return f'<instruct>{task_description}\n<query>{query}'
 
 def get_detailed_example(task_description: str, query: str, response: str) -> str:
     return f'<instruct>{task_description}\n<query>{query}\n<response>{response}'
 
+def get_new_queries(queries, query_max_len, examples_prefix, tokenizer):
+    inputs = tokenizer(
+        queries,
+        max_length=query_max_len - len(tokenizer('<s>', add_special_tokens=False)['input_ids']) - len(
+            tokenizer('\n<response></s>', add_special_tokens=False)['input_ids']),
+        return_token_type_ids=False,
+        truncation=True,
+        return_tensors=None,
+        add_special_tokens=False
+    )
+    prefix_ids = tokenizer(examples_prefix)['input_ids']
+    suffix_ids = tokenizer('\n<response>')['input_ids']
+    new_max_length = (len(prefix_ids) + len(suffix_ids) + query_max_len) // 8 * 8 + 8
+    new_queries = tokenizer.batch_decode(inputs['input_ids'])
+    for i in range(len(new_queries)):
+        new_queries[i] = examples_prefix + new_queries[i] + '\n<response>'
+    return new_max_length, new_queries
+
 task = 'Given a web search query, retrieve relevant passages that answer the query.'
 examples = [
   {'instruct': 'Given a web search query, retrieve relevant passages that answer the query.',
@@ -1795,31 +1813,34 @@ examples = [
 examples = [get_detailed_example(e['instruct'], e['query'], e['response']) for e in examples]
 examples_prefix = '\n\n'.join(examples) + '\n\n'
 queries = [
-    examples_prefix + get_detailed_instruct(task, 'how much protein should a female eat'),
-    examples_prefix + get_detailed_instruct(task, 'summit define')
+    get_detailed_instruct(task, 'how much protein should a female eat'),
+    get_detailed_instruct(task, 'summit define')
 ]
-# No need to add instructions for documents
 documents = [
     "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
     "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
 ]
-input_texts = queries + documents
+query_max_len, doc_max_len = 512, 512
 
 tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-en-icl')
 model = AutoModel.from_pretrained('BAAI/bge-en-icl')
 model.eval()
 
-max_length = 4096
-# Tokenize the input texts
-batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt')
+new_query_max_len, new_queries = get_new_queries(queries, query_max_len, examples_prefix, tokenizer)
+
+query_batch_dict = tokenizer(new_queries, max_length=new_query_max_len, padding=True, truncation=True, return_tensors='pt')
+doc_batch_dict = tokenizer(documents, max_length=doc_max_len, padding=True, truncation=True, return_tensors='pt')
 
 with torch.no_grad():
-	outputs = model(**batch_dict)
-	embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+    query_outputs = model(**query_batch_dict)
+    query_embeddings = last_token_pool(query_outputs.last_hidden_state, query_batch_dict['attention_mask'])
+    doc_outputs = model(**doc_batch_dict)
+    doc_embeddings = last_token_pool(doc_outputs.last_hidden_state, doc_batch_dict['attention_mask'])
     
 # normalize embeddings
-embeddings = F.normalize(embeddings, p=2, dim=1)
-scores = (embeddings[:2] @ embeddings[2:].T) * 100
+query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
+doc_embeddings = F.normalize(doc_embeddings, p=2, dim=1)
+scores = (query_embeddings @ doc_embeddings.T) * 100
 print(scores.tolist())
 ```