mm
/

gte-Qwen2-1.5B-instruct-gguf

Inference Endpoints

Model card Files Files and versions Community

mm commited on Jul 7

Commit

1bba62b

•

1 Parent(s): aa4408f

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -33,6 +33,7 @@ model = Llama.from_pretrained(
     embedding=True,
     n_ctx=max_length,
     n_batch=max_length,
     verbose=False,
 )
 model.tokenize = partial(model.tokenize, special=True)

     embedding=True,
     n_ctx=max_length,
     n_batch=max_length,
+    flash_attn=True,
     verbose=False,
 )
 model.tokenize = partial(model.tokenize, special=True)