Update README.md
Browse files
README.md
CHANGED
@@ -23,15 +23,15 @@ Boston is a great city with many attractions to visit. Here are some popular one
|
|
23 |
If you run with a batch size of 60 you can get a nice throughput even with GEMV:
|
24 |
|
25 |
```
|
26 |
-
[2023-12-
|
27 |
-
[2023-12-
|
28 |
-
[2023-12-
|
29 |
-
step0 time: 1.
|
30 |
-
[2023-12-
|
31 |
-
[2023-12-
|
32 |
-
[2023-12-
|
33 |
-
[2023-12-
|
34 |
-
Time w/o python interpreter load/terminate: 11.
|
35 |
```
|
36 |
|
37 |
|
|
|
23 |
If you run with a batch size of 60 you can get a nice throughput even with GEMV:
|
24 |
|
25 |
```
|
26 |
+
[2023-12-27 14:54:47,967 INFO] Loading checkpoint from /mnt/InternalCrucial4/dataAI/mistral-7B/mistral-instruct-v0.2/mistral-instruct-v0.2-onmt-awq-gemv.pt
|
27 |
+
[2023-12-27 14:54:48,063 INFO] awq_gemv compression of layer ['w_1', 'w_2', 'w_3', 'linear_values', 'linear_query', 'linear_keys', 'final_linear']
|
28 |
+
[2023-12-27 14:54:52,059 INFO] Loading data into the model
|
29 |
+
step0 time: 1.2714881896972656
|
30 |
+
[2023-12-27 14:54:59,180 INFO] PRED SCORE: -0.2316, PRED PPL: 1.26 NB SENTENCES: 59
|
31 |
+
[2023-12-27 14:54:59,180 INFO] Total translation time (s): 6.1
|
32 |
+
[2023-12-27 14:54:59,180 INFO] Average translation time (ms): 103.5
|
33 |
+
[2023-12-27 14:54:59,180 INFO] Tokens per second: 2183.8
|
34 |
+
Time w/o python interpreter load/terminate: 11.222625255584717
|
35 |
```
|
36 |
|
37 |
|