Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -7,6 +7,31 @@ from transformers import AutoTokenizer
|
|
7 |
|
8 |
|
9 |
DESCRIPTION = """
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
"""
|
12 |
|
|
|
7 |
|
8 |
|
9 |
DESCRIPTION = """
|
10 |
+
# Demo: Breeze-7B-Instruct-v0.1
|
11 |
+
|
12 |
+
Breeze-7B is a language model family that builds on top of [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1), specifically intended for Traditional Chinese use.
|
13 |
+
|
14 |
+
[Breeze-7B-Base](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v0.1) is the base model for the Breeze-7B series.
|
15 |
+
It is suitable for use if you have substantial fine-tuning data to tune it for your specific use case.
|
16 |
+
|
17 |
+
[Breeze-7B-Instruct](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0.1) derives from the base model Breeze-7B-Base, making the resulting model amenable to be used as-is for commonly seen tasks.
|
18 |
+
|
19 |
+
[Breeze-7B-Instruct-64k](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1) is a slightly modified version of
|
20 |
+
Breeze-7B-Instruct to enable a 64k-token context length. Roughly speaking, that is equivalent to 88k Traditional Chinese characters.
|
21 |
+
|
22 |
+
The current release version of Breeze-7B is v0.1.
|
23 |
+
|
24 |
+
Practicality-wise:
|
25 |
+
- Breeze-7B-Base expands the original vocabulary with additional 30,000 Traditional Chinese tokens. With the expanded vocabulary, everything else being equal, Breeze-7B operates at twice the inference speed for Traditional Chinese to Mistral-7B and Llama 7B. [See [Inference Performance](#inference-performance).]
|
26 |
+
- Breeze-7B-Instruct can be used as is for common tasks such as Q&A, RAG, multi-round chat, and summarization.
|
27 |
+
- In particular, Breeze-7B-Instruct-64k can perform tasks at a document level, not a chapter level.
|
28 |
+
|
29 |
+
|
30 |
+
Performance-wise:
|
31 |
+
- Breeze-7B-Instruct demonstrates impressive performance in benchmarks for Traditional Chinese and English, when compared to similar sized open-source contemporaries such as Taiwan-LLM-7B/13B-chat, QWen-7B-Chat, and Yi-6B-Chat. [See [Chat Model Performance](#chat-model-performance).]
|
32 |
+
|
33 |
+
|
34 |
+
*A project by the members (in alphabetical order): Chan-Jan Hsu 許湛然, Chang-Le Liu 劉昶樂, Feng-Ting Liao 廖峰挺, Po-Chun Hsu 許博竣, Yi-Chang Chen 陳宜昌, and the supervisor Da-Shan Shiu 許大山.*
|
35 |
|
36 |
"""
|
37 |
|