Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,17 @@
|
|
| 1 |
---
|
| 2 |
title: AtlasChat
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 4.
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
license: gemma
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: AtlasChat
|
| 3 |
+
emoji: 🏔️
|
| 4 |
+
colorFrom: yellow
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 4.36.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
license: gemma
|
| 11 |
---
|
| 12 |
|
| 13 |
+
This is a demo of the small-sized version of [AtlasChat](https://arxiv.org/pdf/2409.17912).
|
| 14 |
+
|
| 15 |
+
Looking for a larger and more powerful version? Try the 9B version in [Hugging Face](https://huggingface.co/mbzuai-paris/atlas-chat-9b).
|
| 16 |
+
|
| 17 |
+
This demo was done using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) library for efficient inference and is running the [`mradermacher/Atlas-Chat-2B-GGUF`](https://huggingface.co/mradermacher/Atlas-Chat-2B-GGUF) version with 8-bit Q8_0 quantization.
|