Hugging Face's logo

Spaces:
ai-forever
/
LIBRA-Leaderboard
Running

App Files Community
ai-forever Cursor commited on
Commit
36a74fd
·
1 Parent(s): bb7d347

Remove local image embeds for HF Hub policy; ignore logo and diagram assets

Browse files
Files changed (2) hide show
  1. .gitignore +4 -0
  2. docs/description.md +0 -7
.gitignore CHANGED
@@ -1 +1,5 @@
1
  hf_token
 
 
 
 
 
1
  hf_token
2
+
3
+ # HF Hub rejects committing binaries to Spaces git; use Space Files UI or Xet — see hub docs
4
+ logo.png
5
+ libra_structure.svg
docs/description.md CHANGED
@@ -1,7 +1,4 @@
1
  # LIBRA: Long Input Benchmark for Russian Analysis
2
- <p align="center">
3
- <img src="logo.png" width="500" />
4
- </p>
5
 
6
  ## LIBRA
7
 
@@ -32,10 +29,6 @@ We recommend **using LIBRA Mini as the primary evaluation suite for model compar
32
 
33
  ## Dataset Structure
34
 
35
- <p align="center">
36
- <img src="libra_structure.svg" width="600" />
37
- </p>
38
-
39
  The datasets are divided into subsets based on context lengths. The table below shows the number of examples per context length for each dataset. Datasets included in **LIBRA Mini** are highlighted in bold. Note that not all datasets cover the full range of context lengths — some are designed for specific length ranges that best suit their task type.
40
 
41
  | **Task** | **4k** | **8k** | **16k** | **32k** | **64k** | **128k** | **256k** | **512k** | | **Total** |
 
1
  # LIBRA: Long Input Benchmark for Russian Analysis
 
 
 
2
 
3
  ## LIBRA
4
 
 
29
 
30
  ## Dataset Structure
31
 
 
 
 
 
32
  The datasets are divided into subsets based on context lengths. The table below shows the number of examples per context length for each dataset. Datasets included in **LIBRA Mini** are highlighted in bold. Note that not all datasets cover the full range of context lengths — some are designed for specific length ranges that best suit their task type.
33
 
34
  | **Task** | **4k** | **8k** | **16k** | **32k** | **64k** | **128k** | **256k** | **512k** | | **Total** |