PhoebusSi/Alpaca-CoT

Issues

• 刚接触ai，大模型等，咨询下这个json是怎么使用的呢

  #187 opened 4 months ago by zzfree2021
  0

• tabular_llm分支提供的数据集存在错误

  #186 opened 5 months ago by 01WarpDrive
  0

• Error when loading sharegpt dataset

  #185 opened 7 months ago by jiangjiadi
  0

• 你好,群二维码过期了,能更新一下么~

  #179 opened a year ago by linqinhong
  6

• 1

  #184 opened a year ago by yhr20000319
  0

• main分支下的readme顺序，以及base模型能否提供huggingface的链接

  #183 opened a year ago by nuocheng
  4

• Adding Contributors Section In readme.md

  #176 opened a year ago by mohitd404
  0

• 你好，能更新下群信息么

  #165 opened a year ago by xyjsjruiliu
  2

• What is the relationship between the data and the link you provided?

  #163 opened a year ago by tingxueronghua
  0

• About the source of the dataset

  #162 opened a year ago by tingxueronghua
  0

• 你好，群二维码过期了

  #154 opened a year ago by aplmikex
  1

• 是否可以提供一个Gdrive和百度云的下载方式

  #149 opened 2 years ago by nuoma
  2

• 是否可以支持qlora

  #150 opened 2 years ago by li-aolong
  0

• inference结果差异比较大，请问是什么原因

  #145 opened 2 years ago by liuzhiyong01
  2

• web.py中缺少--size参数

  #144 opened 2 years ago by zmh908264302
  1

• DataCollatorForLanguageModeling uses the unmasked labels

  #143 opened 2 years ago by shuiyueche
  0

• About the tokenizer

  #131 opened 2 years ago by yusonghust
  0

• The text meaning in zh_helpfulness_context.json in Alpaca-CoT / MOSS / moss-002-sft

  #140 opened 2 years ago by 4daJKong
  0

• ThoughtSource annotated dataset for CoT

  #67 opened 2 years ago by yhyu13
  2

• does it support mutiple nodes mutiple GPU fine tuning？

  #94 opened 2 years ago by qingyuan18
  1

• 8卡V100跑moss OOV

  #124 opened 2 years ago by uloveqian2021
  2

• Prompt设置

  #130 opened 2 years ago by Ricardokevins
  1

• How to use other parameter-efficient methods? Such as Prefix-tuning?

  #115 opened 2 years ago by oriCodesPorter
  2

• GPTeacher Code-Instruct

  #122 opened 2 years ago by teknium1
  1

• 请问如何修改模型的自我认知

  #121 opened 2 years ago by podanshu
  0

• 使用MOSS报错：RuntimeError: expected scalar type Half but found Float

  #106 opened 2 years ago by orangefish08
  7

• ChatGLM的Finetune推荐命令，使用3090 24G会OOM，代码默认使用8Bit量化同样会导致OOM

  #118 opened 2 years ago by StarrickLiu
  1

• ShareGPT Dataset?

  #109 opened 2 years ago by teknium1
  8

• alpaca-belle-cot是指哪个数据？

  #110 opened 2 years ago by shibing624
  1

• chatglm-6B A100，80G显卡，在单机多卡并行时报OOM，把lora改成8了也OOM，改成torchrun也OOM

  #103 opened 2 years ago by hangzeli08
  8

• 为什么我训练的lora的adapter_model.bin最后只有443字节

  #111 opened 2 years ago by SiriusWy
  2

• Integrate GPTeacher?

  #108 opened 2 years ago by teknium1
  1

• ChatGLM-6B的input问题

  #95 opened 2 years ago by aqtalent
  1

• 为什么没有中文的数据集？都是英文的

  #97 opened 2 years ago by lemon-simple
  2

• chatglm6b finetune时使用instruction模板，serve.py推理中无模板

  #91 opened 2 years ago by ykk648
  0

• LaMini-Instruction dataset (2million)

  #93 opened 2 years ago by KnutJaegersberg
  1

• BLOOM微调报错： RuntimeError: GET was unable to find an engine to execute this computation

  #90 opened 2 years ago by YerayL
  1

• Long Form dataset

  #88 opened 2 years ago by KnutJaegersberg
  1

• Flan dataset

  #72 opened 2 years ago by KnutJaegersberg
  1

• huggingface上的数据集无法加载，会报错

  #79 opened 2 years ago by yupeijei1997
  2

• The difference between uniform_finetune.py and finetune.py

  #81 opened 2 years ago by ckx506772099
  0

• 运行predict.py报错

  #74 opened 2 years ago by oriCodesPorter
  2

• 多轮对话报错

  #73 opened 2 years ago by lin1490188
  1

• data xP3 not suitable for chatbot tranining or finetuning?

  #75 opened 2 years ago by yzxyzh
  2

• 这是一个非常棒的工作，但是cot数据集部分，中文的一些翻译可能是有问题的

  #62 opened 2 years ago by yinfupai
  6

• 群聊人数超过200人，无法加入

  #69 opened 2 years ago by ykk648
  1

• 如何使用flan/v2/templates.py把多页文本转格式

  #68 opened 2 years ago by eeric
  1

• Holistic Evaluation of Language Models (HELM) datasets

  #64 opened 2 years ago by yhyu13
  0

• Zero-shot-cot dataset fine-tuned on OpenAI models

  #63 opened 2 years ago by yhyu13
  0

• add sharegpt vicuna dateset

  #60 opened 2 years ago by forex24
  1