Comments (1)
建议加上所有的数据集从头训练,也可以合并 lora 后继续 sft,但应该不如前者
from llama-factory.
Related Issues (20)
- sft llama3-8B deepspeed zero3很慢, GPU利用率100%,但是功率很低 HOT 1
- DBRX using more gpu memory than mixtral 8x22B for fsdp+qlora HOT 1
- 如何添加huggingface api HOT 1
- 多次增量预训练,loss都是从2.8左右开始降低 HOT 1
- How to "full" param train llama2-70B with unsloth? HOT 1
- 图形界面中是否可以指定template? HOT 1
- 在部署拉取新的llama-factory的之后的运行总报错awq_ext HOT 1
- qwen unsloth无效 HOT 1
- Pre-training generates model issues HOT 1
- 如何关闭wandb?我不用nohup的时候可以正常训练,但用nohup跑的时候总是出现以下wandb的error。 HOT 3
- Llama3-8B-Chinese-Chat-GGUF导入到ollama后问题 HOT 1
- 如果我想基于大模型微调一个特定的分类任务,我该选择哪种微调方式呢 HOT 2
- 多节点sft一直卡在这里,微调llama3 8b HOT 1
- How to convert Dolphin-2.9 to LLaMA factory? HOT 1
- 您好,请问在推理过程中设置相同的温度和top p如何生成多样性回答,设置不同的seed?
- wandb 初始化问题 HOT 1
- How to export the finetuned model to GGUF using gradio ui or cli HOT 4
- Running Evaluation过程中出现的错误 HOT 1
- 接issue3537,如何添加自定义参数,
- Hey can u help me with how to upload my dataset for finetuning iam using this notebook: https://colab.research.google.com/drive/1eRTPn37ltBbYsISy9Aw2NuI2Aq5CQrD9?usp=sharing HOT 1
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.