Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -15,21 +15,17 @@ DEFAULT_MAX_NEW_TOKENS = 1024
|
|
15 |
MAX_INPUT_TOKEN_LENGTH = 4000
|
16 |
|
17 |
DESCRIPTION = """
|
18 |
-
# Llama-2 7B Chat
|
19 |
|
20 |
-
|
21 |
-
|
22 |
-
🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
|
23 |
-
|
24 |
-
🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
|
25 |
"""
|
26 |
|
27 |
LICENSE = """
|
28 |
<p/>
|
29 |
|
30 |
---
|
31 |
-
As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
|
32 |
-
this demo is governed by the original [license](https://huggingface.co/spaces/
|
33 |
"""
|
34 |
|
35 |
if not torch.cuda.is_available():
|
|
|
15 |
MAX_INPUT_TOKEN_LENGTH = 4000
|
16 |
|
17 |
DESCRIPTION = """
|
18 |
+
# Chinese Llama-2 7B Chat
|
19 |
|
20 |
+
本空间是对于[Chinese-Llama-2-7b](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b)模型的演示。该模型由LinkSoul开发,基于Llama 2基础模型和自行收集的大规模中英文指令数据集[instruction_merge_set](https://huggingface.co/datasets/LinkSoul/instruction_merge_set)训练得到。
|
|
|
|
|
|
|
|
|
21 |
"""
|
22 |
|
23 |
LICENSE = """
|
24 |
<p/>
|
25 |
|
26 |
---
|
27 |
+
As a derivate work of [Chinese-Llama-2-7b](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b) by LinkSoul and [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
|
28 |
+
this demo is governed by the original [license](https://huggingface.co/spaces/LinkSoul/Chinese-Llama-2-7b/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/LinkSoul/Chinese-Llama-2-7b/blob/main/USE_POLICY.md).
|
29 |
"""
|
30 |
|
31 |
if not torch.cuda.is_available():
|