Spaces:
Paused
Paused
chore: update something
Browse files
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 |
|