q-future
/

co-instruct

Image-Text-to-Text

feature-extraction

Model card Files Files and versions

teowu commited on Jan 15, 2024

Commit

9dd6788

·

verified ·

1 Parent(s): edd457f

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -11,7 +11,8 @@ from transformers import AutoModelForCausalLM
 model = AutoModelForCausalLM.from_pretrained("q-future/co-instruct-preview",
                                              trust_remote_code=True,
-                                             torch_dtype=torch.float16,
                                              device_map={"":"cuda:0"})
 ```

 model = AutoModelForCausalLM.from_pretrained("q-future/co-instruct-preview",
                                              trust_remote_code=True,
+                                             torch_dtype=torch.float16,
+                                             attn_implementation="flash_attention_2",
                                              device_map={"":"cuda:0"})
 ```