lamhieu commited on
Commit
0f942b5
1 Parent(s): bf7aef8

chore: update something

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. app.py +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: Ghost 8B Beta (β, 8k)
3
  emoji: 👻 / 🥸
4
  colorFrom: indigo
5
  colorTo: pink
 
1
  ---
2
+ title: Ghost 8B Beta (β, 8k, Online)
3
  emoji: 👻 / 🥸
4
  colorFrom: indigo
5
  colorTo: pink
app.py CHANGED
@@ -29,7 +29,7 @@ DEFAULT_MAX_NEW_TOKENS = 1536
29
  MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
30
 
31
  DESCRIPTION = """\
32
- # Playground with Ghost 8B Beta (β, 8k)
33
 
34
  **Ghost 8B Beta** model outperforms prominent models such as Llama 3 8B Instruct, GPT 3.5 Turbo in the lc_winrate score. In addition, it also outperforms Claude 3 Opus, Claude 3 Sonnet, GPT-4, and Mistral Large when comparing the winrate score of AlpacaEval 2.0, [*](https://ghost-x.org/docs/models/ghost-8b-beta/). The model comes in two context length versions, [8k](https://huggingface.co/spaces/lamhieu/ghost-8b-beta-8k) and [128k](https://huggingface.co/spaces/lamhieu/ghost-8b-beta-128k), along with multilingual function tools support by default.
35
 
 
29
  MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
30
 
31
  DESCRIPTION = """\
32
+ # Playground with Ghost 8B Beta (β, 8k, Online)
33
 
34
  **Ghost 8B Beta** model outperforms prominent models such as Llama 3 8B Instruct, GPT 3.5 Turbo in the lc_winrate score. In addition, it also outperforms Claude 3 Opus, Claude 3 Sonnet, GPT-4, and Mistral Large when comparing the winrate score of AlpacaEval 2.0, [*](https://ghost-x.org/docs/models/ghost-8b-beta/). The model comes in two context length versions, [8k](https://huggingface.co/spaces/lamhieu/ghost-8b-beta-8k) and [128k](https://huggingface.co/spaces/lamhieu/ghost-8b-beta-128k), along with multilingual function tools support by default.
35