Spaces:
Restarting
on
CPU Upgrade
Restarting
on
CPU Upgrade
Update src/assets/text_content.py
Browse files
src/assets/text_content.py
CHANGED
@@ -6,7 +6,7 @@ BOTTOM_LOGO = """<img src="https://upstage-open-ko-llm-leaderboard-logos.s3.ap-n
|
|
6 |
INTRODUCTION_TEXT = f"""
|
7 |
🚀 The Open Ko-LLM Leaderboard 🇰🇷 objectively evaluates the performance of Korean Large Language Model (LLM).
|
8 |
|
9 |
-
When you submit a model on the "Submit here!" page, it is automatically evaluated. The GPU used for evaluation is operated with the support of
|
10 |
The data used for evaluation consists of datasets to assess reasoning, language understanding, hallucination, and commonsense.
|
11 |
The evaluation dataset is exclusively private and only available for evaluation process.
|
12 |
More detailed information about the benchmark dataset is provided on the “About” page.
|
@@ -58,7 +58,7 @@ Models added here will be automatically evaluated on the KT GPU cluster.
|
|
58 |
## <Some good practices before submitting a model>
|
59 |
|
60 |
### 1️⃣ Make sure you can load your model and tokenizer using AutoClasses
|
61 |
-
```
|
62 |
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
63 |
config = AutoConfig.from_pretrained("your model name", revision=revision)
|
64 |
model = AutoModel.from_pretrained("your model name", revision=revision)
|
@@ -71,7 +71,7 @@ If this step fails, follow the error messages to debug your model before submitt
|
|
71 |
|
72 |
⚠️ Maker sure your model runs with [Eleuther AI Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness)
|
73 |
|
74 |
-
⚠️ If your model needs use_remote_code=True
|
75 |
|
76 |
### 2️⃣ Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
|
77 |
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`!
|
|
|
6 |
INTRODUCTION_TEXT = f"""
|
7 |
🚀 The Open Ko-LLM Leaderboard 🇰🇷 objectively evaluates the performance of Korean Large Language Model (LLM).
|
8 |
|
9 |
+
When you submit a model on the "Submit here!" page, it is automatically evaluated. The GPU used for evaluation is operated with the support of __[KT](https://cloud.kt.com/)__.
|
10 |
The data used for evaluation consists of datasets to assess reasoning, language understanding, hallucination, and commonsense.
|
11 |
The evaluation dataset is exclusively private and only available for evaluation process.
|
12 |
More detailed information about the benchmark dataset is provided on the “About” page.
|
|
|
58 |
## <Some good practices before submitting a model>
|
59 |
|
60 |
### 1️⃣ Make sure you can load your model and tokenizer using AutoClasses
|
61 |
+
```python
|
62 |
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
63 |
config = AutoConfig.from_pretrained("your model name", revision=revision)
|
64 |
model = AutoModel.from_pretrained("your model name", revision=revision)
|
|
|
71 |
|
72 |
⚠️ Maker sure your model runs with [Eleuther AI Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness)
|
73 |
|
74 |
+
⚠️ If your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
|
75 |
|
76 |
### 2️⃣ Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
|
77 |
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`!
|