upload last-token model

modeling_jina_embeddings_c1.py

@@ -39,16 +39,6 @@ def batch(iterable, n=1):
         yield iterable[ndx : min(ndx + n, items)]
 
 
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0]
-    input_mask_expanded = (
-        attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    )
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(
-        input_mask_expanded.sum(1), min=1e-9
-    )
-
-
 def last_token_pooling(model_output, attention_mask):
     token_embeddings = model_output[0]
     left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])