Update app.py
Browse files
app.py
CHANGED
|
@@ -85,7 +85,6 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
| 85 |
MODEL_ID,
|
| 86 |
device_map="auto",
|
| 87 |
quantization_config=quantization_config,
|
| 88 |
-
attn_implementation="flash_attention_2", # Updated Flash Attention 2 parameter
|
| 89 |
torch_dtype=torch.bfloat16
|
| 90 |
)
|
| 91 |
|
|
|
|
| 85 |
MODEL_ID,
|
| 86 |
device_map="auto",
|
| 87 |
quantization_config=quantization_config,
|
|
|
|
| 88 |
torch_dtype=torch.bfloat16
|
| 89 |
)
|
| 90 |
|