xionghonglin / doctorglm Goto Github PK

View Code? Open in Web Editor NEW

723.0 15.0 74.0 44.7 MB

基于ChatGLM-6B的中文问诊模型

Python 55.84% Jupyter Notebook 17.70% HTML 26.45%

chatglm-6b

doctorglm's People

Contributors

Stargazers

Watchers

Forkers

wanddy jamesqfreeman zhaozh10 yuanweilee1 jangocheng flowerjunjie yiilam 731315163 huangweiboy2 dasklarleo yuanck frankli99 greay83 gaohuan2015 daxiajames isperfee huangtao36 meiwupangzi scutcyr leegang wyhfire tian64873493 sinlt youfenghao guanhuashan m2500h dst1213 chenyunzheng teanon chenyu116 kunlun-zhu louwenjie123 ziyi-git allentern guangyingyuan jasonhu55 cderfdsa yaoertech jeffersonchou dadabin butterflyeffectai qqq-tech adambear jlokkc wmm7777 to-be-architect assassindesign youjun301 nanqiai seceum beginner-wj rogercummins wh-flysky cvcuiwei haklmtt gxmdboy teahz thanhpham1987 smn2010 pangpanqiqi trustedsoftware denger03 1zeroorez1 githubmalajava yixuqiu zhuqingyun0510 yuuko-kurisu zstaotao someintuition alexhxun tsu-ke hertera1 just4jc

doctorglm's Issues

prompt designer

您好，我在您的论文中读到您prompt designer模块提取用户输入的关键词，比如疾病名称和症状，然后基于专业的疾病知识库生成简要描述。
请问这个知识库是否可以在github上获得或者通过gpt进行信息抽取

ModuleNotFoundError: No module named 'deep_training.nlp.models.lora'

大佬求助！我去deep_training看了，发现这个包被去掉了，有没有知道怎么办呀！

`chatglm_6b_int4` 库或文件缺失

DoctorGLM/Doctor_GLM/models.py

Line 19 in a307b5d

    
           from chatglm_6b_int4.quantization import quantize, QuantizedEmbedding, QuantizedLinear, load_cpu_kernel

No module named 'load_quantization'

Gradio运行后，会出现“No module named 'load_quantization”，安装pip install load_quantization 后，又会报错“ERROR: Could not find a version that satisfies the requirement load_quantization (from versions: none)”、“ERROR: No matching distribution found for load_quantization”，请问怎么办呢？谢谢！

（似乎不能算pr于是写在issue里了，如有不妥欢迎交流！）

from langchain.document_loaders import DataFrameLoader

file_path = 'data.csv'

df = pd.read_csv(file_path)
df.head()

loader = DataFrameLoader(df,page_content_column="from_name")

docs = loader.load()

idx = 0
qa_dict ={}

for d in docs:
	idx += 1
	# text = d.page_content
	# text = d.page_content
	text = d
	= f"""你是一个聪明的助理。

		给你一段xx相关的技术标准，你必须依据表格想出一个问题和一个对应的答案。

		你想出的问题可以被用来测试xx的专业能力。

		你想出的问题和答案必须和所给文本相关。

		当你想出问题和答案后，你必须用以下格式回复：

		```
		[
			"问题": "$你想出的问题放在这",
			"答案": "$你想出的答案放在这"
		]
		```

		所有在 ``` 中间的内容就是你要回答的格式。

		请想出一个问题与一个答案，用以上指定的列表回复，对于以下文本：
		----------------
		{text}"""

	response, history = model.chat(
		 tokenizer, templ, history=[], max_length=2048)

	while_count = 0
	if_good = True
	while ('以下哪' in response) or ('语言模型' in response) or ('文本' in response) or ('以下是' in response):
			response, history = model.chat(
				tokenizer, templ, history=[], max_length=2048)
			while_count += 1
			if while_count > 10:
				if_good = False
				break
	print(response)

	try:
		if if_good:
			question = response.split('答案：')[0][3:]
			answer = response.split('答案：')[1]
			qa = {}
			qa['问题'] = question
			qa['答案'] = answer
			qa_dict[idx] = qa
		else:
			pass
	except:
			pass
	json.dump(qa_dict, open('qa_dict.json', 'w', encoding='utf-8'),
				  indent=4, ensure_ascii=False)
	
print("json加载完成")