pengxiao-song/LaWGPT
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型
PythonGPL-3.0
Pinned issues
Issues
- 3
卡在webui.sh中的base_model中
#119 opened by tdwaofei - 0
可否公开二次预训练的模型权重?
#157 opened by Eren139 - 0
Output結果一直重複問題
#156 opened by JunTeng1113 - 3
- 0
- 2
- 0
在执行最后的启动命令时,提示如下错误
#151 opened by Bob8852 - 3
环境错误 huggingface能正常打开 但是无法加载预训练模型的tokenizer
#144 opened by lengsihan - 0
复现了大佬的项目,在业务数据上效果还需要优化
#150 opened by zjjlivein - 1
bash ./scripts/webui.sh 无法运行
#146 opened by crazy-canux - 5
卡在pip install -r requirements.txt
#115 opened by Re-hd - 2
- 0
how much cpu memory is needed when merge
#149 opened by liujunchangqq - 1
- 0
Mac M1pro 是否可以使用
#147 opened by haoyang7 - 1
weibu有输入框,但是没有输出框
#141 opened by yangzhenyu6 - 3
运行bash scripts/webui.sh时,遇到UnicodeDecodeError
#121 opened by Daniel-Yang-A - 0
- 0
requests.exceptions.ReadTimeout
#143 opened by imxintian - 0
requests.exceptions.ReadTimeout
#142 opened by imxintian - 1
在本地windows系统的cpu上是否可以运行?
#139 opened by JACKzhuz - 1
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
#130 opened by andrewzheng1618 - 0
Please provide BibTeX citation information
#138 opened by Leymore - 1
按README部署运行不了
#133 opened by BarryCui - 1
在询问的过程中会出现以下错误,有什么好的办法可以解决吗?
#122 opened by caowenling - 1
过于倾向拒绝非具体问题
#129 opened by ttc0419 - 0
微调的时候为何使用的是alpaca template, 而推理的时候却使用law_template?
#136 opened by minmie - 2
- 0
- 1
merge_vocabulary问题
#126 opened by 232525 - 0
請問初級數據是如何生成的
#131 opened by alexaax - 0
LLM技术和训练问题的微信交流群
#111 opened by Anna10071 - 0
- 1
建议完善一下安装环境的说明及常见问题
#113 opened by wltgithub - 0
请问一下在多卡训练的时候,batch_size和micro_batch_size需要乘相应的显卡数吗
#127 opened by mengqunhan - 1
ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'requirements.txt'
#125 opened by githubume - 2
运行webui.sh 报错 TypeError: not a string
#123 opened by zhengyoutan - 1
RuntimeError: unscale_() has already been called on this optimizer since the last update()
#124 opened by mengqunhan - 1
想问一下在指令微调时,是继续在原lora权重基础上训,还是重新训练新的权重
#116 opened by SupritYoung - 2
addmm_impl_cpu_" not implemented for 'Half
#102 opened by hnuzhoulin - 0
use mac to run it?
#120 opened by code-innovator-zyx - 0
请问 Knowledge-based Self-Instruct 相关的代码有吗?想看看
#118 opened by annanfree - 0
技术报告在哪呢?现在怎么302了?
#114 opened by gvalbio - 0
The model weights are not tied. please use the 'tie_weights' method before using the 'infer_auto_device'
#112 opened by guo-zh - 0
使用resume_from_checkpoint参数进行断点续训报keys missing错误。
#110 opened by STHSF - 0
扩表的 Tokenizer 并没有被代码中其它地方使用
#109 opened by twang2218 - 0
- 0
bash webui.sh 是如何运行的
#106 opened by mossee - 0
如果仅运行推理,需要的环境是什么,能否说明一下
#103 opened by bltcn - 0
回答的问题感觉有点矛盾啊
#100 opened by ucas010