Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / SCIR-HI/Huatuo-Llama-Med-Chinese issues and pull requests
#100 - 我用A40微调出现了下列问题,推理没有问题,请问有大佬知道是什么原因吗?
Issue -
State: open - Opened by yihp 11 months ago
- 1 comment
#99 - 我用A40推理过程中报错, RecursionError: maximum recursion depth exceeded,显示栈溢出,下面是完整报错信息,请问是什么问题呢
Issue -
State: open - Opened by yihp 11 months ago
- 4 comments
#98 - 请问融入医学知识库的数据集是data/llama_data.json吗?
Issue -
State: open - Opened by yfangZhang 12 months ago
#97 - 知识微调的代码是否在仓库中?另外推理过程中知识获取在代码哪一步进行了体现?
Issue -
State: open - Opened by yfangZhang 12 months ago
#96 - 请问什么时候公开测试集
Issue -
State: open - Opened by lisdarr 12 months ago
- 2 comments
#95 - 使用cpu进行推理,accelerate报KeyError的问题,key的值随机
Issue -
State: closed - Opened by lotest 12 months ago
#94 - 为何使用Bloom model测试结果有问题?
Issue -
State: open - Opened by wuyuanmm about 1 year ago
- 1 comment
#93 - 但节点多GPU训练
Issue -
State: open - Opened by zjhJOJO about 1 year ago
- 1 comment
#92 - 生成答案重复
Issue -
State: open - Opened by loki1017 about 1 year ago
- 2 comments
#91 - How to finetune on huozi?
Issue -
State: closed - Opened by yongliang-wu about 1 year ago
- 2 comments
#90 - UnicodeDecodeError: 'gbk' codec can't decode byte 0xaf in position 93: illegal multibyte sequence
Issue -
State: open - Opened by cookie925 about 1 year ago
- 2 comments
#89 - RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)
Issue -
State: open - Opened by daiyizheng about 1 year ago
- 2 comments
#88 - 请问数据集什么时候完整公布
Issue -
State: open - Opened by vansin about 1 year ago
- 1 comment
#87 - 使用huozi模型时出现错误
Issue -
State: closed - Opened by nkcsjxd about 1 year ago
- 4 comments
#86 - RecursionError: maximum recursion depth exceeded
Issue -
State: closed - Opened by nkcsjxd about 1 year ago
- 2 comments
#85 - 指令微调的训练集的数据分布
Issue -
State: closed - Opened by zhangyu68 about 1 year ago
- 2 comments
#84 - 您好,您这个项目如何运行起来?
Issue -
State: closed - Opened by endluo about 1 year ago
- 3 comments
#83 - 希望取得联系
Issue -
State: closed - Opened by JimmyMa99 about 1 year ago
- 1 comment
#82 - 如何多卡部署
Issue -
State: closed - Opened by 200109110057Wjy about 1 year ago
- 1 comment
#81 - 请问有打算开发在线体验版吗?
Issue -
State: closed - Opened by mack007liu about 1 year ago
- 1 comment
#80 - 新增基于bloom进行指令微调的LoRA权重的链接
Pull Request -
State: closed - Opened by FlowolfzzZ about 1 year ago
#79 - ValueError: We need an `offload_dir` to dispatch this model according to this `device_map`...
Issue -
State: open - Opened by Pingmin about 1 year ago
#78 - 报错BrokenPipeError: [Errno 32] Broken pipe,完整报错如下,请问这是哪里的问题
Issue -
State: open - Opened by pandazzh2020 about 1 year ago
- 1 comment
#77 - 如何使用微调后的模型
Issue -
State: closed - Opened by handsomexiaoyi about 1 year ago
- 1 comment
#76 - 答非所问
Issue -
State: closed - Opened by gggdroa about 1 year ago
- 3 comments
#75 - NotImplementedError: Cannot copy out of meta tensor; no data!
Issue -
State: open - Opened by sjtuzhaoxh about 1 year ago
- 1 comment
#74 - 预测的结果时乱码
Issue -
State: closed - Opened by handsomexiaoyi about 1 year ago
- 1 comment
#73 - 我设置了cuda:0,但是还是显示Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!
Issue -
State: closed - Opened by handsomexiaoyi about 1 year ago
- 5 comments
#72 - 创建账户需要40字符报错了怎么解决呢wandb.errors.AuthenticationError: The API key you provided is either invalid or missing. If the `WANDB_API_KEY` environment variable is set, make sure it is correct.
Issue -
State: closed - Opened by jiaqingxiang111 about 1 year ago
- 1 comment
#71 - An error occurred while generating the dataset
Issue -
State: closed - Opened by chencoder1 about 1 year ago
- 2 comments
#70 - 是否扩充了llama的分词器
Issue -
State: closed - Opened by zemu121 about 1 year ago
- 3 comments
#69 - 请问推理需要占用多少显存,我40GB运行infer.sh提示:CUDA error: out of memory
Issue -
State: closed - Opened by Macvh about 1 year ago
- 3 comments
#68 - 我执行infer运行时会自动下载模型,但是租用的服务器不让下载,如何手动下载安装模型
Issue -
State: closed - Opened by icewizardry about 1 year ago
- 1 comment
#67 - 如何使用GPT生成训练数据
Issue -
State: closed - Opened by HaimianYu over 1 year ago
- 1 comment
#66 - RuntimeError: "log_softmax_lastdim_kernel_impl" not implemented for 'Half'
Issue -
State: closed - Opened by liulj0507 over 1 year ago
- 1 comment
#65 - Add your paper hyperlink
Issue -
State: closed - Opened by lichaoahcil over 1 year ago
- 1 comment
#64 - 是否支持指定GPU id运行?
Issue -
State: closed - Opened by hackbuteer001 over 1 year ago
- 1 comment
#63 - Med-chatGLM显存不够咋办,都64G显存了,抱歉,因为Med-chatGML没人回复,到这里试一下
Issue -
State: closed - Opened by chenxu126 over 1 year ago
- 1 comment
#62 - 修复安装及adapter_model.bin存储错误问题
Pull Request -
State: closed - Opened by sharpbai over 1 year ago
#61 - 发现好多人提了很多问题,项目上的人回复的很少,这个项目是不是用来炒作的?
Issue -
State: closed - Opened by chenxu126 over 1 year ago
- 1 comment
#60 - CUDA out of memory
Issue -
State: closed - Opened by csyanghan over 1 year ago
- 1 comment
#59 - Add links to Hugging Face
Pull Request -
State: closed - Opened by FlowolfzzZ over 1 year ago
#58 - med模板 prompt input 与 noinput 模板都不包含input, 是不是写错了?
Issue -
State: closed - Opened by liangsh0208 over 1 year ago
- 1 comment
#57 - 模型效果评测
Issue -
State: closed - Opened by toughhou over 1 year ago
- 3 comments
#56 - “结论”信息如何融入多轮对话中
Issue -
State: closed - Opened by toughhou over 1 year ago
- 2 comments
#55 - 为什么使用自己的数据集微调完了,它的回答总是重复我问的?
Issue -
State: closed - Opened by chenxu126 over 1 year ago
- 8 comments
#54 - 使用finetune.py微调代码,最后保存peft训练好的lora模型报错
Issue -
State: closed - Opened by Forever-Young-l over 1 year ago
- 1 comment
#53 - 4 张 3090 上运行 finetune,运行结束报错 UnboundLocalError: local variable 'load_result' referenced before assignment
Issue -
State: closed - Opened by diaojunxian over 1 year ago
- 14 comments
#52 - 为什么使用提供的alpaca 的lora参数推理出来的结果完全不对,胡言乱语
Issue -
State: closed - Opened by HeisenbergSu over 1 year ago
- 5 comments
#51 - 代码的问题
Issue -
State: closed - Opened by wuguangshuo over 1 year ago
- 2 comments
#50 - 无法加载使用alpaca模型
Issue -
State: closed - Opened by WangRongsheng over 1 year ago
#49 - 有兴趣做一个更加实用的健康模型吗?
Issue -
State: closed - Opened by yiming0926 over 1 year ago
- 1 comment
#48 - [BUG]运行infer.py cuda设置失败报错
Issue -
State: closed - Opened by woshicqy over 1 year ago
- 1 comment
#47 - 训练后的数据不理想
Issue -
State: closed - Opened by frog-game over 1 year ago
- 4 comments
#46 - LoRA百度网盘访问密码错误
Issue -
State: closed - Opened by kuyin over 1 year ago
- 2 comments
#45 - 训练数据集的构建
Issue -
State: closed - Opened by yungangwu over 1 year ago
- 7 comments
#44 - 如何复现基于Chinese-alpaca-7b的医学知识和医学文献对话模型?
Issue -
State: closed - Opened by LouisHeck over 1 year ago
- 1 comment
#43 - 基于医学知识库运行infer.sh报错"addmm_impl_cpu_" not implemented for 'Half'
Issue -
State: closed - Opened by wanglumeng over 1 year ago
- 2 comments
#42 - 如何加入自己的中医医疗数据进行训练
Issue -
State: closed - Opened by zj2050 over 1 year ago
- 1 comment
#41 - 运行finetune.py 之后,在infer.py阶段有错误
Issue -
State: closed - Opened by YI52KE over 1 year ago
#40 - 请问作者有没有做 ChatGLM 和 LLaMA 的评测
Issue -
State: closed - Opened by SupritYoung over 1 year ago
- 1 comment
#39 - 我觉得“华驼”这个名字更好
Issue -
State: closed - Opened by devinzhang91 over 1 year ago
- 3 comments
#38 - 请问如何基于中文Alpaca大模型进行指令微调?
Issue -
State: closed - Opened by SupritYoung over 1 year ago
- 3 comments
#37 - 下载后的材料要怎么操作
Issue -
State: closed - Opened by ccccler over 1 year ago
#36 - 申请入群,运行infer文件报错,想请教一下如何解决!
Issue -
State: closed - Opened by moonlight12581 over 1 year ago
- 12 comments
#35 - 申请入群,具体操作不会
Issue -
State: closed - Opened by Aguahanpu over 1 year ago
#34 - chinese-alpaca使用的模板与华驼不一致
Issue -
State: closed - Opened by yuanzhiyong1999 over 1 year ago
- 1 comment
#33 - 你好,感谢开源!希望能开源怎么利用chatgpt 接口进行的多轮对话数据生成!谢谢
Issue -
State: closed - Opened by cristianohello over 1 year ago
- 3 comments
#32 - 百度网盘密码错了啊
Issue -
State: closed - Opened by ScienGU over 1 year ago
- 2 comments
#31 - lora alpaca med
Issue -
State: closed - Opened by imjking over 1 year ago
- 1 comment
#30 - Update README.md
Pull Request -
State: closed - Opened by eltociear over 1 year ago
#29 - eval_loss为nan是什么原因
Issue -
State: closed - Opened by yuanzhiyong1999 over 1 year ago
- 1 comment
#28 - 是不是可以用Text generation web UI来部署
Issue -
State: closed - Opened by yixian3500 over 1 year ago
- 2 comments
#27 - 申请入群
Issue -
State: closed - Opened by herove over 1 year ago
- 21 comments
#26 - 关于SUS的计算
Issue -
State: closed - Opened by thomascong121 over 1 year ago
- 1 comment
#25 - 请问是否以经典中医医书为主?
Issue -
State: closed - Opened by jingrongx over 1 year ago
- 2 comments
#24 - 模型文件应该放在什么位置
Issue -
State: closed - Opened by caichuang0415 over 1 year ago
- 2 comments
#23 - 有没有先进行预训练让llama拥有中文能力
Issue -
State: closed - Opened by yuanzhiyong1999 over 1 year ago
- 4 comments
#22 - 运行infer.sh文件出现错误
Issue -
State: closed - Opened by CodingPeasantzgl over 1 year ago
- 2 comments
#21 - 请问如何利用GPT3.5生成医学文献多轮问答数据?
Issue -
State: closed - Opened by jimyang2008y over 1 year ago
- 11 comments
#20 - 询问一下,运行infer.py,报错TypeError: 'NoneType' object is not subscriptable
Issue -
State: closed - Opened by yujianwei1 over 1 year ago
- 1 comment
#19 - “华佗" or “华驼” ?
Issue -
State: closed - Opened by toughhou over 1 year ago
#18 - ADD Chinese Alpaca
Pull Request -
State: closed - Opened by FlowolfzzZ over 1 year ago
#17 - CUDA Setup failed despite GPU being available.
Issue -
State: closed - Opened by cweihua over 1 year ago
- 2 comments
#16 - 数据集必须是instruct的形式吗?
Issue -
State: closed - Opened by dyabc1 over 1 year ago
- 4 comments
#15 - 运行报错:json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Issue -
State: closed - Opened by Hasen-dc over 1 year ago
- 1 comment
#14 - 是否有用到真实医疗场景数据?
Issue -
State: closed - Opened by kaishxu over 1 year ago
- 1 comment
#13 - 回答效果不太专业,三轮会话后显存超32G
Issue -
State: closed - Opened by gptbert over 1 year ago
- 1 comment
#12 - 与chatGLM-6B比较
Issue -
State: closed - Opened by hanswang73 over 1 year ago
- 3 comments
#11 - 请问这种输出乱码一般是什么原因呢?
Issue -
State: closed - Opened by herobrine19 over 1 year ago
- 1 comment
#10 - 已解决
Issue -
State: closed - Opened by GasolSun36 over 1 year ago
- 1 comment
#9 - Huatuo-Llama-Med-Chinese和Med-ChatGLM这两个项目在医疗问答的表现哪个好
Issue -
State: closed - Opened by lelegogo26 over 1 year ago
- 2 comments
#8 - 与技术无关,单纯的好奇,为什么是“驼“而不是“佗”?
Issue -
State: closed - Opened by haozhi1817 over 1 year ago
- 2 comments
#7 - Update README.md
Pull Request -
State: closed - Opened by eltociear over 1 year ago
#6 - 项目提供的lora没有达到提的效果呀,就给的那几个infer的例子
Issue -
State: closed - Opened by Zombiessss over 1 year ago
- 5 comments
#5 - 运行bash ./scripts/infer.sh 报错
Issue -
State: closed - Opened by XiaohuaC over 1 year ago
- 1 comment
#4 - 关于训练数据的生成
Issue -
State: closed - Opened by ShawnChang-ei over 1 year ago
- 1 comment
#3 - 请问是否有做过微调后与Med-ChatGLM的对比
Issue -
State: closed - Opened by danger-dream over 1 year ago
- 1 comment
#2 - About Huatuo
Issue -
State: closed - Opened by wabyking over 1 year ago
- 2 comments
#1 - 有一个疑问,ChatGLM-Med为什么没有像华佗一样lora微调呢?
Issue -
State: closed - Opened by pogevip over 1 year ago
- 2 comments