Comments (2)
niravlg
commented on July 17, 2024
1
I believe this issue has been mentioned in
#4402
As far as I understand, the above suggested solution changes the prompt used for chosen and rejected responses in DPO which likely effect the training and results. Instead, I believe the implementation should follow from the DPO Trainer's implementation in -
https://github.com/huggingface/trl/blob/main/trl/trainer/dpo_trainer.py
PS - The above issue in not mentioned in my native language. I used ChatGPT to translate it to english. I apologize in advance of any confusion.
from llama-factory.
hiyouga
commented on July 17, 2024
1
fixed
from llama-factory.
Related Issues (20)
- MixtralBlockSparseTop2MLP没有这个
- 推理重复
- 运行qwen-14B时报错：AttributeError: module 'transformers_modules.Qwen-14B-Chat.modeling_qwen' has no attribute 'QWenLMHeadModel' HOT 1
- 麻烦问一下，这个问题后来怎么解决的呀？依赖都已经满足要求了？ HOT 1
- 2张16g P100 显卡，运行qwen2-7b提示显卡版本太低，如何处理？
- DeepSeek-Coder-V2-Lite-Base加载BFloat16报错
- qwen2 sft loss学习率一直是0 HOT 2
- 关于使用LLaMA-Factory在2张A100上全参数微调qwen2-7b-instruct训到中间报错问题
- Help：zero 2 训练大量sft 指令跟随数据后，grad norm 出现NAN，损失为0
- 分类任务的训练是否有ROC AUC指标的展示？
- 新人求指导ImportError: cannot import name 'soft_unicode' from 'markupsafe'
- llamafactory的webui可以在于训练过程中给原有的大模型（如qwen0.5b）扩展词表（加入新的token）吗？该如何实现啊？ HOT 2
- Implementation of Flash Attention 3
- docker部署非常不好用 HOT 1
- 训练时出现运行错误
- 请问这个项目不支持在原有模型基础之上扩展新的token吗？通过命令行和配置文件也无法在预训练阶段扩展词表吗？ HOT 1
- 昇腾NPU推理glm4-9b-chat出现'NoneType' object has no attribute 'do_sample' HOT 2
- 扩充词表 HOT 1
- Where is the prompt template for DeepSeek Coder v2
- 微调过程中词表扩充导致的不匹配问题（已添加resize_vocab: true）
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.