Upload feifeiflorence.py

feifeilib/feifeiflorence.py

@@ -6,6 +6,13 @@ from transformers import (
     AutoModelForCausalLM,
 )
 import torch
+import subprocess
+
+subprocess.run(
+    "pip install flash-attn --no-build-isolation",
+    env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
+    shell=True,
+)
 
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32