k-mktr commited on
Commit
216002b
Β·
verified Β·
1 Parent(s): 335d363

Update config.py

Browse files
Files changed (1) hide show
  1. config.py +18 -6
config.py CHANGED
@@ -5,15 +5,27 @@ from datetime import datetime
5
  import time
6
  import threading
7
 
8
- ARENA_NAME = "# πŸ† The GPU-Poor LLM Gladiator Arena πŸ†"
9
  ARENA_DESCRIPTION = """
10
- Step right up to the arena where frugal meets fabulous in the world of AI!
11
  Watch as our compact contenders (maxing out at 14B parameters) duke it out in a battle of wits and words.
12
- 1. Type your prompt into the text box. Alternatively, click the "🎲" button to receive a random prompt.
13
- 2. Click the "Generate Responses" button to view the models' responses.
14
- 3. Cast your vote for the model that provided the better response. In the event of a Tie, enter a new prompt before continuing the battle.
15
- 4. Check out the Leaderboard to see how models rank against each other.
 
 
 
 
 
 
 
 
 
 
 
16
  More info: [README.md](https://huggingface.co/spaces/k-mktr/gpu-poor-llm-arena/blob/main/README.md)
 
17
  """
18
 
19
  # Ollama API configuration
 
5
  import time
6
  import threading
7
 
8
+ ARENA_NAME = "# πŸ† The GPU-Poor LLM Gladiator Arena πŸ† v25.03"
9
  ARENA_DESCRIPTION = """
10
+ **Step right up to the arena where frugal meets fabulous in the world of AI!**
11
  Watch as our compact contenders (maxing out at 14B parameters) duke it out in a battle of wits and words.
12
+
13
+ What started as a simple experiment has grown into a popular platform for evaluating compact language models.
14
+ As the arena continues to expand with more models, features, and battles, it requires computational resources to maintain and improve.
15
+ **If you find this project valuable and would like to support its development, consider sponsoring:**
16
+ [![Sponsor](https://img.shields.io/badge/sponsor-30363D?style=for-the-badge&logo=GitHub-Sponsors&logoColor=#EA4AAA)](https://github.com/sponsors/k-mktr)
17
+
18
+ <details>
19
+ <summary>πŸ“– How to Use</summary>
20
+
21
+ 1. To start the battle, go to the 'Battle Arena' tab.
22
+ 2. Type your prompt into the text box. Alternatively, click the "🎲" button to receive a random prompt.
23
+ 3. Click the "Generate Responses" button to view the models' responses.
24
+ 4. Cast your vote for the model that provided the better response. In the event of a Tie, enter a new prompt before continuing the battle.
25
+ 5. Check out the Leaderboard to see how models rank against each other.
26
+
27
  More info: [README.md](https://huggingface.co/spaces/k-mktr/gpu-poor-llm-arena/blob/main/README.md)
28
+ </details>
29
  """
30
 
31
  # Ollama API configuration