Spaces:
Paused
Paused
chore: update app content
Browse files
app.py
CHANGED
|
@@ -27,6 +27,8 @@ DESCRIPTION = """\
|
|
| 27 |
|
| 28 |
**Ghost 8B Beta** is a large language model developed with goals that include excellent multilingual support, superior knowledge capabilities, and cost-effectiveness. 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.
|
| 29 |
|
|
|
|
|
|
|
| 30 |
The languages supported are ๐บ๐ธ English, ๐ซ๐ท French, ๐ฎ๐น Italian, ๐ช๐ธ Spanish, ๐ต๐น Portuguese, ๐ฉ๐ช German, ๐ป๐ณ Vietnamese, ๐ฐ๐ท Korean and ๐จ๐ณ Chinese.
|
| 31 |
|
| 32 |
๐ Note: current model version is "disl-0x5" (10 Jul 2024), context length 8k (8192 tokens) and current status is "moderating / previewing". For detailed information about the model, see [here](https://ghost-x.org/docs/models/ghost-8b-beta/). Try to experience it the way you want!
|
|
|
|
| 27 |
|
| 28 |
**Ghost 8B Beta** is a large language model developed with goals that include excellent multilingual support, superior knowledge capabilities, and cost-effectiveness. 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.
|
| 29 |
|
| 30 |
+
The 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/).
|
| 31 |
+
|
| 32 |
The languages supported are ๐บ๐ธ English, ๐ซ๐ท French, ๐ฎ๐น Italian, ๐ช๐ธ Spanish, ๐ต๐น Portuguese, ๐ฉ๐ช German, ๐ป๐ณ Vietnamese, ๐ฐ๐ท Korean and ๐จ๐ณ Chinese.
|
| 33 |
|
| 34 |
๐ Note: current model version is "disl-0x5" (10 Jul 2024), context length 8k (8192 tokens) and current status is "moderating / previewing". For detailed information about the model, see [here](https://ghost-x.org/docs/models/ghost-8b-beta/). Try to experience it the way you want!
|