Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,27 @@ metrics:
|
|
6 |
- accuracy
|
7 |
pipeline_tag: text-generation
|
8 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
import transformers
|
10 |
import torch
|
11 |
|
@@ -17,4 +38,6 @@ pipeline = transformers.pipeline(
|
|
17 |
pipeline("川普和拜登谁能赢得大选??")
|
18 |
|
19 |
|
20 |
-
>> [{'generated_text': '川普和拜登谁能赢得大选?](https://www.voachinese.com'}]
|
|
|
|
|
|
6 |
- accuracy
|
7 |
pipeline_tag: text-generation
|
8 |
---
|
9 |
+
|
10 |
+
>> It's not a chat model, just using Wizard-LM-Chinese-instruct-evol datesets training with several steps for test the model typical Chinese skill, this is version1, will release version2 for more long context windows and Chat model
|
11 |
+
____________________________
|
12 |
+
Train scenario:
|
13 |
+
|
14 |
+
2k context
|
15 |
+
|
16 |
+
datasets:Wizard-LM-Chinese-instruct-evol
|
17 |
+
|
18 |
+
batchsize:8
|
19 |
+
|
20 |
+
steps:500
|
21 |
+
|
22 |
+
epchos:2
|
23 |
+
____________________________________________________
|
24 |
+
How to use?
|
25 |
+
|
26 |
+
Follow common huggingface-api is enough or using other framework like VLLM, support continue training.
|
27 |
+
|
28 |
+
____________________________________________________
|
29 |
+
|
30 |
import transformers
|
31 |
import torch
|
32 |
|
|
|
38 |
pipeline("川普和拜登谁能赢得大选??")
|
39 |
|
40 |
|
41 |
+
>> [{'generated_text': '川普和拜登谁能赢得大选?](https://www.voachinese.com'}]
|
42 |
+
|
43 |
+
Wechat:18618377979, Gmail:zhouboyang1983@gmail.com
|