MindNLP ChatGLM-6B StreamChat
本案例基于MindNLP和ChatGLM-6B实现一个聊天应用。
1 环境配置
%%capture captured_output
# 实验环境已经预装了mindspore==2.2.14，如需更换mindspore版本，可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14
!pip install mdtex2html
配置网络线路
!export HF_ENDPOINT=https://hf-mirror.com
2 代码开发
下载权重大约需要10分钟
from mindnlp.transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import gradio as gr
import mdtex2htmlmodel = AutoModelForSeq2SeqLM.from_pretrained('ZhipuAI/ChatGLM-6B', mirror="modelscope").half()
model.set_train(False)
tokenizer = AutoTokenizer.from_pretrained('ZhipuAI/ChatGLM-6B', mirror="modelscope")
0%| | 0.00/773 [00:00<?, ?B/s]0%| | 0.00/32.6k [00:00<?, ?B/s]Downloading shards: 0%| | 0/8 [00:00<?, ?it/s]0%| | 0.00/1.62G [00:00<?, ?B/s]0%| | 0.00/1.75G [00:00<?, ?B/s]0%| | 0.00/1.84G [00:00<?, ?B/s]0%| | 0.00/1.78G [00:00<?, ?B/s]0%| | 0.00/1.75G [00:00<?, ?B/s]0%| | 0.00/1.75G [00:00<?, ?B/s]0%| | 0.00/1.00G [00:00<?, ?B/s]0%| | 0.00/1.00G [00:00<?, ?B/s]Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]0%| | 0.00/441 [00:00<?, ?B/s]0%| | 0.00/2.58M [00:00<?, ?B/s]
可以修改下列参数和prompt体验模型
prompt = '你好'
history = []
response, _ = model.chat(tokenizer, prompt, history=history, max_length=20)
response
|The dtype of attention mask (Float32) is not bool/'你好👋！我是人工智能助手 ChatGLM-6B'
prompt = '你好 请问文本解码原理'
history = []
response, _ = model.chat(tokenizer, prompt, history=history, max_length=20)
response
-'文本解码是指将文本转换为计算机能够理解的形式的过程'
prompt = '你好 请问文本解码原理,请列出数学原理'
history = []
response, _ = model.chat(tokenizer, prompt, history=history, max_length=200)
response
-'文本解码是指将文本编码为数字形式的过程，通常使用数字信号处理技术来实现。\n\n文本解码的数学原理可以概括为以下几个方面：\n\n1. 文本编码原理：文本编码是指将文本转换为压缩格式的过程。常用的文本编码方法包括：压缩编码、词袋模型、长短时记忆网络等。这些模型通常使用数学模型来描述文本的特征和模式，并使用这些模型来预测下一个单词或字符。\n\n2. 数字信号处理技术：数字信号处理技术是指使用数字电路和算法来处理数字信号的方法。文本解码通常需要使用数字信号处理技术来提取文本的特征，并使用数字信号处理技术来压缩和解码文本。\n\n3. 熵编码原理：熵编码是指使用熵值来编码文本的方法。熵值是一个统计量，表示文本的不确定性。常用的熵编码方法包括：信息熵、高斯熵等'
print("yangge mindspore打卡23天之MindNLP ChatGLM-6B StreamChat 2024 07 11")
yangge mindspore打卡23天之MindNLP ChatGLM-6B StreamChat 2024 07 11
文本解码原理--以MindNLP为例
回顾：自回归语言模型
根据前文预测下一个单词
一个文本序列的概率分布可以分解为每个词基于其上文的条件概率的乘积
- 𝑊_0:初始上下文单词序列
- 𝑇: 时间步
- 当生成EOS标签时，停止生成。
MindNLP/huggingface Transformers提供的文本生成方法
Greedy search
在每个时间步𝑡都简单地选择概率最高的词作为当前输出词:
𝑤_𝑡=𝑎𝑟𝑔𝑚𝑎𝑥_𝑤 𝑃(𝑤|𝑤_(1:𝑡−1))
按照贪心搜索输出序列(“The”,“nice”,“woman”) 的条件概率为：0.5 x 0.4 = 0.2
缺点: 错过了隐藏在低概率词后面的高概率词，如：dog=0.5, has=0.9
环境准备
%%capture captured_output
# 实验环境已经预装了mindspore==2.2.14，如需更换mindspore版本，可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14
!pip uninstall mindvision -y
!pip uninstall mindinsight -y
Found existing installation: mindvision 0.1.0
Uninstalling mindvision-0.1.0:Successfully uninstalled mindvision-0.1.0
[33mWARNING: Skipping mindinsight as it is not installed.[0m[33m
[0m
# 该案例在 mindnlp 0.3.1 版本完成适配，如果发现案例跑不通，可以指定mindnlp版本，执行`!pip install mindnlp==0.3.1`
!pip install mindnlp
#greedy_searchfrom mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')# generate text until the output length (which includes the context length) reaches 50
greedy_output = model.generate(input_ids, max_length=50)print("Output:\n" + 100 * '-')
print(tokenizer.decode(greedy_output[0], skip_special_tokens=True))
Building prefix dict from the default dictionary ...
Loading model from cache /tmp/jieba.cache
Loading model cost 1.016 seconds.
Prefix dict has been built successfully.0%| | 0.00/26.0 [00:00<?, ?B/s]0%| | 0.00/0.99M [00:00<?, ?B/s]0%| | 0.00/446k [00:00<?, ?B/s]0%| | 0.00/1.29M [00:00<?, ?B/s]0%| | 0.00/665 [00:00<?, ?B/s]0%| | 0.00/523M [00:00<?, ?B/s]Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog, but I'm not sure if I'll ever be able to walk with my dog. I'm not sure if I'll ever be able to walk with my dog.I'm not sure if I'll
Beam search
Beam search通过在每个时间步保留最可能的 num_beams 个词，并从中最终选择出概率最高的序列来降低丢失潜在的高概率序列的风险。如图以 num_beams=2 为例:
(“The”,“dog”,“has”) : 0.4 * 0.9 = 0.36
(“The”,“nice”,“woman”) : 0.5 * 0.4 = 0.20
优点：一定程度保留最优路径
缺点：1. 无法解决重复问题；2. 开放域生成效果差
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')# activate beam search and early_stopping
beam_output = model.generate(input_ids, max_length=50, num_beams=5, early_stopping=True
)print("Output:\n" + 100 * '-')
print(tokenizer.decode(beam_output[0], skip_special_tokens=True))
print(100 * '-')# set no_repeat_ngram_size to 2
beam_output = model.generate(input_ids, max_length=50, num_beams=5, no_repeat_ngram_size=2, early_stopping=True
)print("Beam search with ngram, Output:\n" + 100 * '-')
print(tokenizer.decode(beam_output[0], skip_special_tokens=True))
print(100 * '-')# set return_num_sequences > 1
beam_outputs = model.generate(input_ids, max_length=50, num_beams=5, no_repeat_ngram_size=2, num_return_sequences=5, early_stopping=True
)# now we have 3 output sequences
print("return_num_sequences, Output:\n" + 100 * '-')
for i, beam_output in enumerate(beam_outputs):print("{}: {}".format(i, tokenizer.decode(beam_output, skip_special_tokens=True)))
print(100 * '-')Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I don't think I'll ever be able to walk with her again.""I don't think I
----------------------------------------------------------------------------------------------------
Beam search with ngram, Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I'm not sure what to say to that," she said. "I mean, it's not like I'm
----------------------------------------------------------------------------------------------------
return_num_sequences, Output:
----------------------------------------------------------------------------------------------------
0: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I'm not sure what to say to that," she said. "I mean, it's not like I'm
1: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I'm not sure what to say to that," she said. "I mean, it's not like she's
2: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I'm not sure what to say to that," she said. "I mean, it's not like we're
3: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I'm not sure what to say to that," she said. "I mean, it's not like I've
4: I enjoy walking with my cute dog, but I don't think I'll ever be able to walk with her again.""I'm not sure what to say to that," she said. "I mean, it's not like I can
----------------------------------------------------------------------------------------------------
Beam search issues
缺点：1. 无法解决重复问题；2. 开放域生成效果差
Repeat problem
n-gram 惩罚:
将出现过的候选词的概率设置为 0
设置no_repeat_ngram_size=2 ，任意 2-gram 不会出现两次
Notice: 实际文本生成需要重复出现
Sample
根据当前条件概率分布随机选择输出词𝑤_𝑡
(“car”) ～P(w∣"The")
(“drives”) ～P(w∣"The",“car”)
优点：文本生成多样性高
缺点：生成文本不连续
import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')mindspore.set_seed(0)
# activate sampling and deactivate top_k by setting top_k sampling to 0
sample_output = model.generate(input_ids, do_sample=True, max_length=50, top_k=0
)print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))
Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog Neddy as much as I'd like. Keep up the good work Neddy!"I realized what Neddy meant when he first launched the website. "Thank you so much for joining."I
Temperature
降低softmax 的temperature使 P(w∣w1:t−1)分布更陡峭
增加高概率单词的似然并降低低概率单词的似然
import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')mindspore.set_seed(1234)
# activate sampling and deactivate top_k by setting top_k sampling to 0
sample_output = model.generate(input_ids, do_sample=True, max_length=50, top_k=0,temperature=0.7
)print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))
Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog and have never had a problem with her until now.A large dog named Chucky managed to get a few long stretches of grass on her back and ran around with it for about 5 minutes, ran around
TopK sample
选出概率最大的 K 个词，重新归一化，最后在归一化后的 K 个词中采样
TopK sample problems
将采样池限制为固定大小 K ：
- 在分布比较尖锐的时候产生胡言乱语
- 在分布比较平坦的时候限制模型的创造力
import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')mindspore.set_seed(0)
# activate sampling and deactivate top_k by setting top_k sampling to 0
sample_output = model.generate(input_ids, do_sample=True, max_length=50, top_k=50
)print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))
Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog.She's always up for some action, so I have seen her do some stuff with it.Then there's the two of us.The two of us I'm talking about were
Top-P sample
在累积概率超过概率 p 的最小单词集中进行采样，重新归一化
采样池可以根据下一个词的概率分布动态增加和减少
import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')mindspore.set_seed(0)# deactivate top_k sampling and sample only from 92% most likely words
sample_output = model.generate(input_ids, do_sample=True, max_length=50, top_p=0.92, top_k=0
)print("Output:\n" + 100 * '-')
print(tokenizer.decode(sample_output[0], skip_special_tokens=True))
Output:
----------------------------------------------------------------------------------------------------
I enjoy walking with my cute dog Neddy as much as I'd like. Keep up the good work Neddy!"I realized what Neddy meant when he first launched the website. "Thank you so much for joining."I
top_k_top_p
import mindspore
from mindnlp.transformers import GPT2Tokenizer, GPT2LMHeadModeltokenizer = GPT2Tokenizer.from_pretrained("iiBcai/gpt2", mirror='modelscope')# add the EOS token as PAD token to avoid warnings
model = GPT2LMHeadModel.from_pretrained("iiBcai/gpt2", pad_token_id=tokenizer.eos_token_id, mirror='modelscope')# encode context the generation is conditioned on
input_ids = tokenizer.encode('I enjoy walking with my cute dog', return_tensors='ms')mindspore.set_seed(0)
# set top_k = 50 and set top_p = 0.95 and num_return_sequences = 3
sample_outputs = model.generate(input_ids,do_sample=True,max_length=50,top_k=5,top_p=0.95,num_return_sequences=3
)print("Output:\n" + 100 * '-')
for i, sample_output in enumerate(sample_outputs):print("{}: {}".format(i, tokenizer.decode(sample_output, skip_special_tokens=True)))
Output:
----------------------------------------------------------------------------------------------------
0: I enjoy walking with my cute dog."My dog loves the smell of the dog. I'm so happy that she's happy with me."I love to walk with my dog. I'm so happy that she's happy
1: I enjoy walking with my cute dog. I'm a big fan of my cat and her dog, but I don't have the same enthusiasm for her. It's hard not to like her because it is my dog.My husband, who
2: I enjoy walking with my cute dog, but I'm also not sure I would want my dog to walk alone with me."She also told The Daily Beast that the dog is very protective."I think she's very protective of
print("yanggemindspore打卡23天之文本解码原理-以MindNLP为例 2024 07 11")
yanggemindspore打卡23天之文本解码原理-以MindNLP为例 2024 07 11
