Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
FinancialSupport
commited on
Commit
•
f467176
1
Parent(s):
0318673
Update src/about.py
Browse files- src/about.py +2 -2
src/about.py
CHANGED
@@ -50,8 +50,8 @@ Per tutti questi task, a un punteggio migliore corrisponde una performance maggi
|
|
50 |
|
51 |
## Reproducibility
|
52 |
Per riprodurre i risultati scaricate la <a href="https://github.com/EleutherAI/lm-evaluation-harness" target="_blank"> Eleuther AI Language Model Evaluation Harness </a> ed eseguite:
|
53 |
-
* lm-eval --model hf --model_args pretrained=<vostro modello> --tasks hellaswag_it,arc_it --device cuda:0 --batch_size
|
54 |
-
* lm-eval --model hf --model_args pretrained=<vostro modello>, --tasks m_mmlu_it --num_fewshot 5 --device cuda:0 --batch_size
|
55 |
"""
|
56 |
|
57 |
EVALUATION_QUEUE_TEXT = """
|
|
|
50 |
|
51 |
## Reproducibility
|
52 |
Per riprodurre i risultati scaricate la <a href="https://github.com/EleutherAI/lm-evaluation-harness" target="_blank"> Eleuther AI Language Model Evaluation Harness </a> ed eseguite:
|
53 |
+
* lm-eval --model hf --model_args pretrained=<vostro modello> --tasks hellaswag_it,arc_it --device cuda:0 --batch_size 1;
|
54 |
+
* lm-eval --model hf --model_args pretrained=<vostro modello>, --tasks m_mmlu_it --num_fewshot 5 --device cuda:0 --batch_size 1
|
55 |
"""
|
56 |
|
57 |
EVALUATION_QUEUE_TEXT = """
|