Spaces:
Sleeping
Sleeping
bloat half precision
Browse files
app.py
CHANGED
|
@@ -5,7 +5,7 @@ from threading import Thread
|
|
| 5 |
|
| 6 |
|
| 7 |
tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/saiga_llama3_8b")
|
| 8 |
-
model = AutoModelForCausalLM.from_pretrained("IlyaGusev/saiga_llama3_8b"
|
| 9 |
model = model #.to('cuda')
|
| 10 |
|
| 11 |
|
|
|
|
| 5 |
|
| 6 |
|
| 7 |
tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/saiga_llama3_8b")
|
| 8 |
+
model = AutoModelForCausalLM.from_pretrained("IlyaGusev/saiga_llama3_8b", torch_dtype=torch.bfloat16)
|
| 9 |
model = model #.to('cuda')
|
| 10 |
|
| 11 |
|