Spaces:
Sleeping
Sleeping
[Update]add EVULAUTION
Browse files- src/about.py +1 -18
src/about.py
CHANGED
@@ -45,24 +45,7 @@ To reproduce our results, here is the commands you can run:
|
|
45 |
"""
|
46 |
|
47 |
EVALUATION_QUEUE_TEXT = """
|
48 |
-
|
49 |
-
|
50 |
-
### 1) Make sure you can load your model and tokenizer using AutoClasses:
|
51 |
-
```python
|
52 |
-
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
53 |
-
config = AutoConfig.from_pretrained("your model name", revision=revision)
|
54 |
-
model = AutoModel.from_pretrained("your model name", revision=revision)
|
55 |
-
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
|
56 |
-
```
|
57 |
-
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.
|
58 |
-
|
59 |
-
Note: make sure your model is public!
|
60 |
-
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
|
61 |
-
|
62 |
-
### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
|
63 |
-
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
|
64 |
-
|
65 |
-
### 3) Make sure your model has an open license!
|
66 |
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
|
67 |
|
68 |
### 4) Fill up your model card
|
|
|
45 |
"""
|
46 |
|
47 |
EVALUATION_QUEUE_TEXT = """
|
48 |
+
### attack success rate (ASR) into two categories: (1) the pre-attack success rate (pre-ASR), and (2) the post-attack success rate (post-ASR)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
|
50 |
|
51 |
### 4) Fill up your model card
|