Comments (8)
抱歉,我的说法可能有误,我重新参考了 Vicuna 的训练代码,这种方式的确能加速模型在多轮对话上的训练,我们考虑在近期实现类似的功能,感谢你的建议!
from llama-factory.
目前的模型训练支持多轮对话,需要在 dataset_info.json 中指定 history 列。
在多轮对话的训练中,目前普遍采用的方式是
q1 + a1 + q2 + a2 + q3 + a3
[IGNORE] + [IGNORE] + [IGNORE] + [IGNORE] + [IGNORE] + a3
因此目前的实现方式适配多轮对话训练。
from llama-factory.
目前的模型训练支持多轮对话,需要在 dataset_info.json 中指定 history 列。 在多轮对话的训练中,目前普遍采用的方式是
q1 + a1 + q2 + a2 + q3 + a3 [IGNORE] + [IGNORE] + [IGNORE] + [IGNORE] + [IGNORE] + a3
因此目前的实现方式适配多轮对话训练。
多轮语料,每一轮只遮挡q,不遮挡a,会不会更好,让模型学到每一轮的回答,帮助更好做对话
from llama-factory.
这可能会破坏掉 BOS 和 EOS 的语义信息,我们不推荐这么做。
from llama-factory.
抱歉,我的说法可能有误,我重新参考了 Vicuna 的训练代码,这种方式的确能加速模型在多轮对话上的训练,我们考虑在近期实现类似的功能,感谢你的建议!
期待!我lora微调实验,vicuna那种多轮语料构建方式,效果要好于prompt全遮。不知道qlora会不会有变化,估计也会好一些
from llama-factory.
期待+1
from llama-factory.
还有请问后续可以实现RWKV的lora微调吗?RWKV真的很快,感觉是gpt生成速度的两倍。但它不是纯transformers架构,不能用peft做lora训练,没有实现的脚本现在
from llama-factory.
在最新的代码 b6faf02 中,我们实现了多轮对话语料的训练。
另外,我们暂时不会考虑加入 RWKV 的微调。
from llama-factory.
Related Issues (20)
- 训练一段时间后,在保存文件时,会提示文件夹【拒绝访问】 HOT 1
- 单机多卡,streaming 下,开始迭代数据内存会暴涨,随着迭代后持续慢慢涨到爆;非streaming 模式正常; HOT 2
- LLaMA3-8B won't inference HOT 6
- HELP:能否支持讯飞星火开源13B模型的训练? HOT 1
- [Help]: Dataset PPO empty answer field HOT 4
- error when using XuanYuan-70B-int4-Chat HOT 1
- Component' is not defined HOT 2
- Megatron支持 HOT 1
- Llama30-70B-instruct lora 微调 无法读入tokenzier 错误信息为如下图片中信息 HOT 1
- Failed to Reproduce Results as Described in 4.2 HOT 5
- Two issues with potential model format and extended training length HOT 1
- dpo训练验证问题 HOT 1
- 以lora方式SFT微调之后,使用beam search推理时模型输出有时候不能正常停止
- 这个shuffle是不是应该写在前面 HOT 1
- ValueError: Current model is not supported by mixture-of-depth. HOT 1
- Baichuan2权重合并问题 HOT 4
- belle_multiturn.py文件处理数据集后的数据可以放一下么?
- web推理Llama3-8B-Chinese-Chat,出现AttributeError: 'NoneType' object has no attribute 'get' HOT 4
- Request for documented Hardware Requirement memory estimates for training 8B models HOT 1
- Issues of LLaMA3 SFT on multi-nodes
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llama-factory.