Upload README.md with huggingface_hub

README.md

@@ -77,7 +77,8 @@ print(scores) # [0.00027803096387751553, 0.9948403768236574]
 
 ```python
 from FlagEmbedding import FlagLLMReranker
-reranker = FlagLLMReranker('BAAI/bge-reranker-v2-gemma', use_bf16=True) # Setting use_bf16 to True speeds up computation with a slight performance degradation
+reranker = FlagLLMReranker('BAAI/bge-reranker-v2-gemma', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+# reranker = FlagLLMReranker('BAAI/bge-reranker-v2-gemma', use_bf16=True) # You can also set use_bf16=True to speed up computation with a slight performance degradation
 
 score = reranker.compute_score(['query', 'passage'])
 print(score)
@@ -90,7 +91,8 @@ print(scores)
 
 ```python
 from FlagEmbedding import LayerWiseFlagLLMReranker
-reranker = LayerWiseFlagLLMReranker('BAAI/bge-reranker-v2-minicpm-layerwise', use_bf16=True) # Setting use_bf16 to True speeds up computation with a slight performance degradation
+reranker = LayerWiseFlagLLMReranker('BAAI/bge-reranker-v2-minicpm-layerwise', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+# reranker = LayerWiseFlagLLMReranker('BAAI/bge-reranker-v2-minicpm-layerwise', use_bf16=True) # You can also set use_bf16=True to speed up computation with a slight performance degradation
 
 score = reranker.compute_score(['query', 'passage'], cutoff_layers=[28]) # Adjusting 'cutoff_layers' to pick which layers are used for computing the score.
 print(score)
@@ -230,7 +232,7 @@ def get_inputs(pairs, tokenizer, prompt=None, max_length=1024):
             return_tensors='pt',
     )
 
-tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-v2-minicpm-layerwise', trust_remote_code=True, torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-v2-minicpm-layerwise', trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained('BAAI/bge-reranker-v2-minicpm-layerwise', trust_remote_code=True, torch_dtype=torch.bfloat16)
 model = model.to('cuda')
 model.eval()