Spaces:
Runtime error
Runtime error
Update model.py (#3)
Browse files- Update model.py (2336c12fe980b8af144cae4ae4d1a7c32a7c3c22)
Co-authored-by: Nguyen Tan Phat <[email protected]>
model.py
CHANGED
|
@@ -3,10 +3,11 @@ str_cmd1 = 'pip install "unsloth[colab-new] @ git+https://github.com/unslothai/u
|
|
| 3 |
str_cmd2 = 'pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes'
|
| 4 |
os.system(str_cmd1)
|
| 5 |
os.system(str_cmd2)
|
|
|
|
| 6 |
|
| 7 |
|
| 8 |
from unsloth import FastLanguageModel
|
| 9 |
-
|
| 10 |
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
|
| 11 |
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
|
| 12 |
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
|
|
|
|
| 3 |
str_cmd2 = 'pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes'
|
| 4 |
os.system(str_cmd1)
|
| 5 |
os.system(str_cmd2)
|
| 6 |
+
os.environ["CUDA_VISIBLE_DEVICES"] = "1" # or "0,1" for multiple GPUs
|
| 7 |
|
| 8 |
|
| 9 |
from unsloth import FastLanguageModel
|
| 10 |
+
import torch
|
| 11 |
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
|
| 12 |
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
|
| 13 |
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
|