Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ If no comment is made, None data regarding the product or shipping will be retur
|
|
| 9 |
|
| 10 |
Used to quantization method like this ;
|
| 11 |
|
| 12 |
-
|
| 13 |
import torch
|
| 14 |
#quantizasyon yöntemi 4 bit hassasiyetiyle yapacak.
|
| 15 |
quant_config = BitsAndBytesConfig(
|
|
@@ -18,12 +18,12 @@ quant_config = BitsAndBytesConfig(
|
|
| 18 |
bnb_4bit_compute_dtype=torch.float16, #maliyeti de düşürmüş olduk, hızı da artırdık
|
| 19 |
bnb_4bit_use_double_quant=True, # True model increases accuracy but causes it to work more costly.
|
| 20 |
) #np4 saves more memory
|
| 21 |
-
|
| 22 |
|
| 23 |
|
| 24 |
Here.. This code contains important steps to optimize LLM's memory usage and processing time.
|
| 25 |
It is important to improve the performance and resource utilization of the model.
|
| 26 |
-
|
| 27 |
#20GB model
|
| 28 |
model = AutoModelForCausalLM.from_pretrained(
|
| 29 |
pretrained_model_name_or_path=base_model, #used "meta-llama/Meta-Llama-3-8B-Instruct"
|
|
@@ -34,4 +34,4 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
| 34 |
)
|
| 35 |
model.config.use_cache = False
|
| 36 |
model.config.pretraining_tp = 1
|
| 37 |
-
|
|
|
|
| 9 |
|
| 10 |
Used to quantization method like this ;
|
| 11 |
|
| 12 |
+
|
| 13 |
import torch
|
| 14 |
#quantizasyon yöntemi 4 bit hassasiyetiyle yapacak.
|
| 15 |
quant_config = BitsAndBytesConfig(
|
|
|
|
| 18 |
bnb_4bit_compute_dtype=torch.float16, #maliyeti de düşürmüş olduk, hızı da artırdık
|
| 19 |
bnb_4bit_use_double_quant=True, # True model increases accuracy but causes it to work more costly.
|
| 20 |
) #np4 saves more memory
|
| 21 |
+
|
| 22 |
|
| 23 |
|
| 24 |
Here.. This code contains important steps to optimize LLM's memory usage and processing time.
|
| 25 |
It is important to improve the performance and resource utilization of the model.
|
| 26 |
+
|
| 27 |
#20GB model
|
| 28 |
model = AutoModelForCausalLM.from_pretrained(
|
| 29 |
pretrained_model_name_or_path=base_model, #used "meta-llama/Meta-Llama-3-8B-Instruct"
|
|
|
|
| 34 |
)
|
| 35 |
model.config.use_cache = False
|
| 36 |
model.config.pretraining_tp = 1
|
| 37 |
+
|