vince62s commited on
Commit
8626604
1 Parent(s): e08fb2f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -9
README.md CHANGED
@@ -22,15 +22,16 @@ Absolutely, Boston is rich in history and culture. Here are some must-visit attr
22
  If you run with a batch size of 60 you can get a nice throughput:
23
 
24
  ```
25
- [2023-12-20 13:17:58,837 INFO] Loading checkpoint from /mnt/InternalCrucial4/dataAI/mistral-7B/mistral-instruct-v0.2/Mistral-7B-instruct-onmt-awq-gemm.pt
26
- [2023-12-20 13:17:58,938 INFO] aawq_gemm compression of layer ['w_1', 'w_2', 'w_3', 'linear_values', 'linear_query', 'linear_keys', 'final_linear']
27
- [2023-12-20 13:18:02,923 INFO] Loading data into the model
28
- step0 time: 1.271669864654541
29
- [2023-12-20 13:18:09,028 INFO] PRED SCORE: -0.2166, PRED PPL: 1.24 NB SENTENCES: 59
30
- [2023-12-20 13:18:09,028 INFO] Total translation time (s): 5.1
31
- [2023-12-20 13:18:09,028 INFO] Average translation time (ms): 87.1
32
- [2023-12-20 13:18:09,028 INFO] Tokens per second: 2494.1
33
- Time w/o python interpreter load/terminate: 10.200786590576172
 
34
  ```
35
 
36
 
 
22
  If you run with a batch size of 60 you can get a nice throughput:
23
 
24
  ```
25
+ [2023-12-27 11:57:35,513 INFO] Loading checkpoint from /mnt/InternalCrucial4/dataAI/mistral-7B/mistral-instruct-v0.2/mistral-instruct-v0.2-onmt-awq-gemm.pt
26
+ [2023-12-27 11:57:35,603 INFO] awq_gemm compression of layer ['w_1', 'w_2', 'w_3', 'linear_values', 'linear_query', 'linear_keys', 'final_linear']
27
+ [2023-12-27 11:57:39,574 INFO] Loading data into the model
28
+ step0 time: 1.2474071979522705
29
+ [2023-12-27 11:57:45,686 INFO] PRED SCORE: -0.2316, PRED PPL: 1.26 NB SENTENCES: 59
30
+ [2023-12-27 11:57:45,686 INFO] Total translation time (s): 5.2
31
+ [2023-12-27 11:57:45,686 INFO] Average translation time (ms): 87.7
32
+ [2023-12-27 11:57:45,686 INFO] Tokens per second: 2576.9
33
+ Time w/o python interpreter load/terminate: 10.182368755340576
34
+
35
  ```
36
 
37