Comments (9)
请问用的是repo里面的数据吗?还是自己的数据?
from self-llm.
用的repo嬛嬛那个数据集
from self-llm.
您好,我这边刚拉下来跑完,没有出现问题:
LoRa微调本身就是不保存权重的,它只保存lora微调的部分,加载的时候需要peft进行二者一起加载,细节可参考同目录下的md文件:
from self-llm.
我之前都是在notebook里面跑的 现在跑的py文件还是一样呢
from self-llm.
你应该是前面的某一步搞错了,我们这边复现的结果loss是逐步下降的。请检查你之前的步骤。
from self-llm.
我也遇到了一样的问题,按照文档跑的,loss 没有下降
from self-llm.
我出现了跟楼主一样的问题,也是loss变成了0.0,也没有生成模型文件
from self-llm.
将 peft 降级至 0.6.2 可以解决问题
from self-llm.
你好请问一下你训练完之后是如何保存lora的权重到本地的?
llm = AutoModelForCausalLM.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True).cuda()
model = get_peft_model(llm, lora_config).cuda()
model.save_pretrained("trained_lora_weights")
请问是使用类似上述的代码保存的吗?我这么写有问题吗?为什么无法保存lora权重到本地?
from self-llm.
Related Issues (20)
- 【非Issues!讨论帖】通过lora微调的qianwen和直接使用system来预设的区别貌似不是很大 HOT 1
- ChatGLM3-6B微调后成哑巴了(字面意思) HOT 4
- 我想我可不可提交给PR支持一下BlueLM我们的蓝心大模型 HOT 1
- 关于模型的api部署,能否推出高性能的异步版本、例如使用vllm、或者fastchat等工具 HOT 1
- 请问chatglm模型Lora微调完成之后,如何加载新模型? HOT 8
- Qwen-1.5-4B LLM推理bug HOT 3
- chatglm3-6b fastapi调用 HOT 1
- 建议按照顺序撰写README部分教程 HOT 1
- 与FastChat的区别
- 多卡报错,Qwen1.5-7B-Chat FastApi 部署调用 HOT 3
- 请问ChatGLM3微调中的数据集huanhuan的在哪获取? HOT 3
- qwen-vl
- deepseek lora HOT 2
- LLaMA3-8B-Instruct+lora使用A800(80GB显存)微调长度8192 HOT 1
- 请问LLAMA3,里面是按1.2.3.4的顺序来分别执行吗? HOT 6
- peft训练完成,参考的是04-Qwen-7B-Chat Lora 微调.ipynb,但是重新载入模型时,提示peft版本问题,用的是model = AutoModelForCausalLM.from_pretrained("../output/Qwen/checkpoint-1300/", trust_remote_code=True).eval(),提示的错误时ValueError: The version of PEFT you are using is not compatible, please use a version that is greater than 0.5.0 HOT 2
- 想问下在这个项目下的lora微调和Chatglm3官方微调的demo的数据格式怎么不一样呀 HOT 1
- 报错asyncio.run() cannot be called from a running event loop,辛苦大佬们看看 HOT 6
- InternLM2 缺少包 HOT 2
- Building wheel for flash-attn (setup.py) ... - 卡住了。 HOT 4
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 self-llm.