chore: update something
Browse files
app.py
CHANGED
@@ -85,7 +85,7 @@ bootstrap();
|
|
85 |
DESCRIPTION = """\
|
86 |
# Ghost 8B Beta (ฮฒ, 128k)
|
87 |
|
88 |
-
**Ghost 8B Beta** outperforms leading models like Llama 3.1 8B Instruct and GPT-3.5 Turbo in lc_winrate scores. It also surpasses Claude 3 Opus, Claude 3 Sonnet, GPT-4, and Mistral Large in AlpacaEval 2.0 winrate scores. The model offers 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), both with built-in multilingual function support.
|
89 |
|
90 |
Supported languages: ๐ฌ๐ง English, ๐ป๐ณ Vietnamese, ๐ฐ๐ท Korean, ๐ช๐ธ Spanish, ๐ต๐น Portuguese, ๐จ๐ณ Chinese, ๐ซ๐ท French, ๐ฎ๐น Italian, ๐ฉ๐ช German, ๐ฏ๐ต Japanese, ๐ท๐บ Russian, ๐ต๐ฑ Polish, ๐ณ๐ฑ Dutch, ๐ฎ๐ณ Hindi, ๐น๐ท Turkish, ๐ฎ๐ฉ Indonesian.
|
91 |
|
|
|
85 |
DESCRIPTION = """\
|
86 |
# Ghost 8B Beta (ฮฒ, 128k)
|
87 |
|
88 |
+
**Ghost 8B Beta** outperforms leading models like Llama 3.1 8B Instruct and GPT-3.5 Turbo in lc_winrate scores. It also surpasses Claude 3 Opus, Claude 3 Sonnet, GPT-4, and Mistral Large in AlpacaEval 2.0 winrate scores. The model offers 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), both with built-in multilingual function support. See details about the model [here](https://ghost-x.org/docs/models/ghost-8b-beta), download from [HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608).
|
89 |
|
90 |
Supported languages: ๐ฌ๐ง English, ๐ป๐ณ Vietnamese, ๐ฐ๐ท Korean, ๐ช๐ธ Spanish, ๐ต๐น Portuguese, ๐จ๐ณ Chinese, ๐ซ๐ท French, ๐ฎ๐น Italian, ๐ฉ๐ช German, ๐ฏ๐ต Japanese, ๐ท๐บ Russian, ๐ต๐ฑ Polish, ๐ณ๐ฑ Dutch, ๐ฎ๐ณ Hindi, ๐น๐ท Turkish, ๐ฎ๐ฉ Indonesian.
|
91 |
|