Commit
·
628e857
1
Parent(s):
4518b0b
Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ pipeline_tag: text-generation
|
|
7 |
---
|
8 |
<div style="text-align:center">
|
9 |
<!-- <img src="https://big-cheng.com/k2/k2.png" alt="k2-logo" width="200"/> -->
|
10 |
-
<h2>📈 CFGPT: Chinese Financial Assistant with Large Language Model (CFGPT1-
|
11 |
</div>
|
12 |
|
13 |
## Introduction
|
@@ -16,93 +16,25 @@ We introduce **CFGPT**, an open-source language model trained by firstly further
|
|
16 |
As for preliminary evaluation, we use CFBenchmark-Basic.
|
17 |
CFGPT outperforms the baselines on objective and subjective tasks compared to several baseline models with similar parameters.
|
18 |
|
19 |
-
In this repository, we will share the
|
20 |
|
21 |
-
- [
|
22 |
|
23 |
## How to Use
|
24 |
|
25 |
-
|
26 |
-
|
27 |
-
Clone [CFGPT]() repository, create a Python environment, and activate it via the following command
|
28 |
-
```bash
|
29 |
-
git clone https://github.com/TongjiFinLab/CFGPT.git
|
30 |
-
cd CFGPT
|
31 |
-
conda create -n env_name python=3.10
|
32 |
-
source activate env_name
|
33 |
-
pip install -r requirements.txt
|
34 |
-
```
|
35 |
-
|
36 |
-
**2. Use CFGPT1-sft-7B-LoRA**
|
37 |
-
|
38 |
-
```python
|
39 |
-
from transformers import AutoModel, AutoTokenizer
|
40 |
-
from peft import PeftModel
|
41 |
-
base_model = 'TongjiFinLab/CFGPT1-pt-7B'
|
42 |
-
lora_weights = 'TongjiFinLab/CFGPT1-sft-7B-LoRA'
|
43 |
-
device_map = 'cuda:0'
|
44 |
-
tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)
|
45 |
-
model = AutoModel.from_pretrained(
|
46 |
-
base_model,
|
47 |
-
trust_remote_code=True,
|
48 |
-
device_map=device_map,
|
49 |
-
torch_dtype=torch.bfloat16
|
50 |
-
)
|
51 |
-
model = PeftModel.from_pretrained(
|
52 |
-
model,
|
53 |
-
lora_weights,
|
54 |
-
device_map=device_map,
|
55 |
-
)
|
56 |
-
model = model.eval()
|
57 |
-
inputs = tokenizer("""你是一名金融从业者,请对这篇新闻进行情感分析。请从(中性、积极、消极)中选取答案。新闻内容:挖贝快讯:特步国际发布2023年第二季度中国内地业务营运状况,披露截至2023年6月30日止3个月零售销售实现高双位数同比增长(包括线上线下渠道),零售折扣水平约七五折。同时,2022年7月MSCI首次予以特步ESG评级,一年后评级表现即迎来提升。明晟MSCI上调特步ESG评级,由“BB”升至“BBB”。\n回答:""", return_tensors='pt').to('cuda:4')
|
58 |
-
pred = model.generate(**inputs, max_new_tokens=64, do_sample=False, repetition_penalty=1.0)
|
59 |
-
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True).split('回答:')[1])
|
60 |
-
```
|
61 |
|
62 |
## 简介
|
63 |
|
64 |
**CFGPT**是一个开源的语言模型,首先通过在收集和清理的中国金融文本数据(CFData-pt)上进行继续预训练,包括金融领域特定数据(公告、金融文章、金融考试、金融新闻、金融研究论文)和通用数据(维基百科),然后使用知识密集的指导调整数据(CFData-sft)进行微调。
|
65 |
我们使用CFBenchmark-Basic进行初步评估。与几个具有相似参数的基线模型相比,CFGPT在识别,分类和生成任务上表现优越。
|
66 |
|
67 |
-
|
68 |
|
69 |
-
- [
|
70 |
|
71 |
## 如何使用
|
72 |
|
73 |
-
|
74 |
-
|
75 |
-
克隆[CFGPT]()的仓库,创建一个Python环境,并通过以下命令激活它:
|
76 |
-
```bash
|
77 |
-
git clone https://github.com/TongjiFinLab/CFGPT.git
|
78 |
-
cd CFGPT
|
79 |
-
conda create -n env_name python=3.10
|
80 |
-
source activate env_name
|
81 |
-
pip install -r requirements.txt
|
82 |
-
```
|
83 |
-
|
84 |
-
**2. 使用 CFGPT1-sft-7B-LoRA**
|
85 |
-
|
86 |
-
```python
|
87 |
-
from transformers import AutoModel, AutoTokenizer
|
88 |
-
from peft import PeftModel
|
89 |
-
base_model = 'TongjiFinLab/CFGPT1-pt-7B'
|
90 |
-
lora_weights = 'TongjiFinLab/CFGPT1-sft-7B-LoRA'
|
91 |
-
device_map = 'cuda:0'
|
92 |
-
tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)
|
93 |
-
model = AutoModel.from_pretrained(
|
94 |
-
base_model,
|
95 |
-
trust_remote_code=True,
|
96 |
-
device_map=device_map,
|
97 |
-
torch_dtype=torch.bfloat16
|
98 |
-
)
|
99 |
-
model = PeftModel.from_pretrained(
|
100 |
-
model,
|
101 |
-
lora_weights,
|
102 |
-
device_map=device_map,
|
103 |
-
)
|
104 |
-
model = model.eval()
|
105 |
-
inputs = tokenizer("""你是一名金融从业者,请���这篇新闻进行情感分析。请从(中性、积极、消极)中选取答案。新闻内容:挖贝快讯:特步国际发布2023年第二季度中国内地业务营运状况,披露截至2023年6月30日止3个月零售销售实现高双位数同比增长(包括线上线下渠道),零售折扣水平约七五折。同时,2022年7月MSCI首次予以特步ESG评级,一年后评级表现即迎来提升。明晟MSCI上调特步ESG评级,由“BB”升至“BBB”。\n回答:""", return_tensors='pt').to(device_map)
|
106 |
-
pred = model.generate(**inputs, max_new_tokens=64, do_sample=False, repetition_penalty=1.0)
|
107 |
-
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True).split('回答:')[1])
|
108 |
-
```
|
|
|
7 |
---
|
8 |
<div style="text-align:center">
|
9 |
<!-- <img src="https://big-cheng.com/k2/k2.png" alt="k2-logo" width="200"/> -->
|
10 |
+
<h2>📈 CFGPT: Chinese Financial Assistant with Large Language Model (CFGPT1-pt-7b)</h2>
|
11 |
</div>
|
12 |
|
13 |
## Introduction
|
|
|
16 |
As for preliminary evaluation, we use CFBenchmark-Basic.
|
17 |
CFGPT outperforms the baselines on objective and subjective tasks compared to several baseline models with similar parameters.
|
18 |
|
19 |
+
In this repository, we will share the further pretrained model.
|
20 |
|
21 |
+
- [Pretrained Model](https://huggingface.co/TongjiFinLab/CFGPT1-pt-7B): Full model weights after further pretraining with the chinese finance text corpus to comply with the InternLM model license.
|
22 |
|
23 |
## How to Use
|
24 |
|
25 |
+
The CFGPT1-pt-7b is a pre-trained model, which has not undergone supervised fine-tuning with a instruction data. Therefore, it is not advisable to use this model for financial tasks.
|
26 |
+
Please refer to [CFGPT]() Github repo for further usage.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
## 简介
|
29 |
|
30 |
**CFGPT**是一个开源的语言模型,首先通过在收集和清理的中国金融文本数据(CFData-pt)上进行继续预训练,包括金融领域特定数据(公告、金融文章、金融考试、金融新闻、金融研究论文)和通用数据(维基百科),然后使用知识密集的指导调整数据(CFData-sft)进行微调。
|
31 |
我们使用CFBenchmark-Basic进行初步评估。与几个具有相似参数的基线模型相比,CFGPT在识别,分类和生成任务上表现优越。
|
32 |
|
33 |
+
在这个仓库中,我们将分享以下继续预训练的模型。
|
34 |
|
35 |
+
- [Pretrained Model](https://huggingface.co/TongjiFinLab/CFGPT1-pt-7B): 在中国金融文本语料库上进行进一步预训练且符合InternLM模型许可的完整模型权重。
|
36 |
|
37 |
## 如何使用
|
38 |
|
39 |
+
这个模型是一个预训练的模型,还没有经历过指令数据库的有监督微调,因此不建议使用该模型执行相关金融任务。
|
40 |
+
具体使用,请参考[CFGPT]()的Github仓库。
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|