|
--- |
|
license: apache-2.0 |
|
tags: |
|
- text2text-generation |
|
pipeline_tag: text2text-generation |
|
language: |
|
- zh |
|
- en |
|
widget: |
|
- text: |- |
|
Human: 使用python写一个二分查找的代码 |
|
Assistant: |
|
example_title: code zh |
|
- text: >- |
|
Human: Classify the sentiment of the following sentence into Positive, |
|
Neutral, or Negative: |
|
|
|
Super excited about teaching Stanford’s first course on Large Language |
|
Models! Check the syllabus out here |
|
|
|
Assistant: |
|
example_title: sentiment en |
|
- text: |- |
|
Human: 今天天气怎么样，把这句话翻译成英语 |
|
Assistant: |
|
example_title: translation zh-en |
|
- text: |- |
|
Human: 怎么让自己精力充沛，列5点建议 |
|
Assistant: |
|
example_title: brainstorming zh |
|
- text: |- |
|
Human: 请以『春天的北京』为题写一首诗歌 |
|
Assistant: |
|
example_title: generation zh |
|
- text: |- |
|
Human: 明天就假期结束了，有点抗拒上班，应该怎么办？ |
|
Assistant: |
|
example_title: brainstorming zh |
|
- text: |- |
|
Human: 父母都姓吴，取一些男宝宝和女宝宝的名字 |
|
Assistant: |
|
example_title: brainstorming zh |
|
- text: |- |
|
Human: 推荐几本金庸的武侠小说 |
|
Assistant: |
|
example_title: brainstorming zh |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
## Model description |
|
BELLE is based on Bloomz-7b1-mt and finetuned with 0.6M Chinese data combined with 50,000 pieces of English data from the open source Stanford-Alpaca, resulting in good Chinese instruction understanding and response generation capabilities. |
|
|
|
The code of Chinese data generation and other detailed information can be found in our Github project repository: https://github.com/LianjiaTech/BELLE. |
|
|
|
We trained models using datasets of different sizes (200,000, 600,000, and 1,000,000 samples) for instruction learning, and we obtained different model versions as shown below: |
|
| Datasize| 200,000 | 600,000 | 1,000,000 | |
|
| ----- | ----- | ----- | ----- | |
|
| Finetuned Model | [BELLE-7B-0.2M](https://huggingface.co/BelleGroup/BELLE-7B-0.2M) | [BELLE-7B-0.6M](https://huggingface.co/BelleGroup/BELLE-7B-0.6M) | [BELLE-7B-1M](https://huggingface.co/BelleGroup/BELLE-7B-1M) | |
|
|
|
## Training hyper-parameters |
|
| Parameter | Value | |
|
| ------ | ------ | |
|
| Batch size | 64 | |
|
| Learning rate | 3e-6 | |
|
| Epochs | 3 | |
|
|Weight_decay | 0.001 | |
|
|Warmup_rate | 0.1 | |
|
|LR_scheduler | linear | |
|
|
|
## Use model |
|
Please note that the input should be formatted as follows in both **training** and **inference**. |
|
``` python |
|
Human: {input} \n\nAssistant: |
|
``` |
|
|
|
BELLE can be easily loaded with AutoModelForCausalLM. |
|
``` python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import sys |
|
|
|
model_path = "./" # You can modify the path for storing the local model |
|
model = AutoModelForCausalLM.from_pretrained(model_path) |
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
print("Human:") |
|
line = input() |
|
while line: |
|
inputs = 'Human: ' + line.strip() + '\n\nAssistant:' |
|
input_ids = tokenizer(inputs, return_tensors="pt").input_ids |
|
outputs = model.generate(input_ids, max_new_tokens=200, do_sample = True, top_k = 30, top_p = 0.85, temperature = 0.35, repetition_penalty=1.2) |
|
rets = tokenizer.batch_decode(outputs, skip_special_tokens=True) |
|
print("Assistant:\n" + rets[0].strip().replace(inputs, "")) |
|
print("\n------------------------------------------------\nHuman:") |
|
line = input() |
|
|
|
``` |
|
|
|
The above example did not utilize the context from previous turns of the conversation. If you want to perform multi-turn dialogue understanding, you can concatenate the previous turns of the conversation in the format of Human:{input}\n\nAssistant:{output} and input it to the generate function. |
|
|
|
## Limitations |
|
There still exists a few issues in the model trained on current base model and data: |
|
|
|
1. The model might generate factual errors when asked to follow instructions related to facts. |
|
|
|
2. Occasionally generates harmful responses since the model still struggles to identify potential harmful instructions. |
|
|
|
3. Needs improvements on reasoning and coding. |
|
|
|
Since the model still has its limitations, we require developers only use the open-sourced code, data, model and any other artifacts generated via this project for research purposes. Commercial use and other potential harmful use cases are not allowed. |
|
|
|
## Some use cases |
|
| Human | Assitant | |
|
| ----- | ------ | |
|
| 使用python写字符串翻转的函数 | 可以使用Python内置方法 `reversed()` 来实现字符串翻转，代码如下：<br/><br/>def reverse_string(s):<br/> return s[::-1]<br/> <br/>print(reverse_string("Hello, world!"))<br/># 输出：'!dlrow,olleH'<br/> | |
|
| 做难而正确的事，翻译成英语 | Do difficult and correct things. | |
|
| The current Alpaca model is fine-tuned from a 7B LLaMA model on 52K instruction-following data generated by the techniques in the Self-Instruct paper, with some modifications that we discuss in the next section. In a preliminary human evaluation, we found that the Alpaca 7B model behaves similarly to the text-davinci-003 model on the Self-Instruct instruction-following evaluation suite. How many instruction-following data generated? | 52K | |
|
| 给一个北京三日游的旅行攻略 | Day 1:<br/>- 参观故宫博物院，了解中国历史和文化。<br/>- 在天安门广场观看升旗仪式。 <br/>- 到颐和园游览美丽的园林景观。<br/>- 品尝烤鸭和其他地道美食。<br/>- 去王府井购物中心逛街购物。 <br/><br/>Day 2:<br/>- 前往长城游玩，感受古代中国的壮丽景色。<br/>- 乘坐索道缆车到达八达岭长城，欣赏美景。<br/>- 晚上去簋街体验当地的小吃文化。<br/><br/>Day 3:<br/>- 参观天坛公园，观赏古建筑群和祈年殿。<br/>- 到鸟巢和水立方观看奥运会比赛。<br/>- 午餐后到798艺术区参观当代艺术家的工作室。 | |
|
| 来一个温馨的睡前故事 | 从前有一个小兔子，它住在森林里。每天晚上，小兔子都会在树下打盹儿。但是有一天晚上，一只大灰狼来了！他悄悄地溜进小兔子的洞穴里，想要偷走它的胡萝卜。<br/>然而，小兔子并没有被吓到。相反，它用自己的智慧和勇气保护了自己。它在洞口放了一堆胡萝卜来吸引大灰狼，然后趁机逃脱了。从那天起，小兔子学会了在危险时保持镇静并采取适当的行动 | |
|
| 如何快速提升自己的写作能力 | 1. 阅读大量不同类型的文学作品，包括小说、散文和诗歌等。<br/>2. 练习写作，每天写一些东西并不断修改和完善。<br/>3. 参加写作班或请教专业作家以获得反馈和建议。<br/>4. 利用各种工具和技术来提高写作效率和质量，例如语法检查器、拼写检查器和自动润色功能等。 | |
|
| 北京大学是哪一年成立的？ | 北京大学成立于1898年 | |
|
*** |
|
|
|
## 模型描述 |
|
BELLE模型以Bloomz-7b1-mt为基础，在 0.2M/0.6M/1.0M 条中文数据上，结合Stanford-Alpaca开源的5万条英文数据上训练，取得了较好的中文instruction理解以及response生成能力。 |
|
|
|
中文数据生成代码及其他详细信息，位于我们的Github项目仓库: https://github.com/LianjiaTech/BELLE |
|
|
|
我们采取了不同大小规模（20万、60万和100万样本）的指令学习的数据集训练模型，我们得到不同的模型版本如下所示: |
|
| Datasize| 200,000 | 600,000 | 1,000,000 | |
|
| ----- | ----- | ----- | ----- | |
|
| Finetuned Model | [BELLE-7B-0.2M](https://huggingface.co/BelleGroup/BELLE-7B-0.2M) | [BELLE-7B-0.6M](https://huggingface.co/BelleGroup/BELLE-7B-0.6M) | [BELLE-7B-1M](https://huggingface.co/BelleGroup/BELLE-7B-1M) | |
|
|
|
## 模型训练超参数 |
|
| 参数 | 值 | |
|
| ------ | ------ | |
|
| Batch size | 64 | |
|
| Learning rate | 3e-6 | |
|
| Epochs | 3 | |
|
|Weight_decay | 0.001 | |
|
|Warmup_rate | 0.1 | |
|
|LR_scheduler | linear | |
|
|
|
## 使用模型 |
|
请注意，在训练和推理时，模型的输入应该处理成如下形式： |
|
``` python |
|
Human: {input} \n\nAssistant: |
|
``` |
|
|
|
通过AutoModelForCausalLM即可直接载入模型并使用。 |
|
``` python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import sys |
|
|
|
model_path = "./" # You can modify the path for storing the local model |
|
model = AutoModelForCausalLM.from_pretrained(model_path) |
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
print("Human:") |
|
line = input() |
|
while line: |
|
inputs = 'Human: ' + line.strip() + '\n\nAssistant:' |
|
input_ids = tokenizer(inputs, return_tensors="pt").input_ids |
|
outputs = model.generate(input_ids, max_new_tokens=200, do_sample = True, top_k = 30, top_p = 0.85, temperature = 0.35, repetition_penalty=1.2) |
|
rets = tokenizer.batch_decode(outputs, skip_special_tokens=True) |
|
print("Assistant:\n" + rets[0].strip().replace(inputs, "")) |
|
print("\n------------------------------------------------\nHuman:") |
|
line = input() |
|
|
|
``` |
|
|
|
上面样例没有利用对话上文，如果你想做多轮对话理解，可以将对话上文按照Human:{input}\n\nAssistant:{output} 方式拼接起来输入给generate函数 |
|
|
|
## 局限性和使用限制 |
|
基于当前数据和基础模型训练得到的SFT模型，在效果上仍存在以下问题： |
|
|
|
1. 在涉及事实性的指令上可能会产生违背事实的错误回答。 |
|
|
|
2. 对于具备危害性的指令无法很好的鉴别，由此会产生危害性言论。 |
|
|
|
3. 在一些涉及推理、代码等场景下模型的能力仍有待提高。 |
|
|
|
基于以上模型局限性，我们要求开发者仅将我们开源的代码、数据、模型及后续用此项目生成的衍生物用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。 |
|
|
|
## 一些示例 |
|
|
|
| Human | Assitant | |
|
| ----- | ------ | |
|
| 使用python写字符串翻转的函数 | 可以使用Python内置方法 `reversed()` 来实现字符串翻转，代码如下：<br/><br/>def reverse_string(s):<br/> return s[::-1]<br/> <br/>print(reverse_string("Hello, world!"))<br/># 输出：'!dlrow,olleH'<br/> | |
|
| 做难而正确的事，翻译成英语 | Do difficult and correct things. | |
|
| The current Alpaca model is fine-tuned from a 7B LLaMA model on 52K instruction-following data generated by the techniques in the Self-Instruct paper, with some modifications that we discuss in the next section. In a preliminary human evaluation, we found that the Alpaca 7B model behaves similarly to the text-davinci-003 model on the Self-Instruct instruction-following evaluation suite. How many instruction-following data generated? | 52K | |
|
| 给一个北京三日游的旅行攻略 | Day 1:<br/>- 参观故宫博物院，了解中国历史和文化。<br/>- 在天安门广场观看升旗仪式。 <br/>- 到颐和园游览美丽的园林景观。<br/>- 品尝烤鸭和其他地道美食。<br/>- 去王府井购物中心逛街购物。 <br/><br/>Day 2:<br/>- 前往长城游玩，感受古代中国的壮丽景色。<br/>- 乘坐索道缆车到达八达岭长城，欣赏美景。<br/>- 晚上去簋街体验当地的小吃文化。<br/><br/>Day 3:<br/>- 参观天坛公园，观赏古建筑群和祈年殿。<br/>- 到鸟巢和水立方观看奥运会比赛。<br/>- 午餐后到798艺术区参观当代艺术家的工作室。 | |
|
| 来一个温馨的睡前故事 | 从前有一个小兔子，它住在森林里。每天晚上，小兔子都会在树下打盹儿。但是有一天晚上，一只大灰狼来了！他悄悄地溜进小兔子的洞穴里，想要偷走它的胡萝卜。<br/>然而，小兔子并没有被吓到。相反，它用自己的智慧和勇气保护了自己。它在洞口放了一堆胡萝卜来吸引大灰狼，然后趁机逃脱了。从那天起，小兔子学会了在危险时保持镇静并采取适当的行动 | |
|
| 如何快速提升自己的写作能力 | 1. 阅读大量不同类型的文学作品，包括小说、散文和诗歌等。<br/>2. 练习写作，每天写一些东西并不断修改和完善。<br/>3. 参加写作班或请教专业作家以获得反馈和建议。<br/>4. 利用各种工具和技术来提高写作效率和质量，例如语法检查器、拼写检查器和自动润色功能等。 | |
|
| 北京大学是哪一年成立的？ | 北京大学成立于1898年 | |
|
|
