Comments (3)
你好,训练参数如何配置,模型需要下载放到对应目录吗
- 制作数据集:
cd scripts
bash train_full.sh -m dataset
or
bash train_lora.sh -m dataset
or
bash train_ptv2.sh -m dataset - 训练
cd scripts
bash train_full.sh -m train
or
bash train_lora.sh -m train
or
bash train_ptv2.sh -m train
默认配置文件是: scripts/config/train_pl.yaml
其他参数可以根据需求修改配置
from qwen_finetuning.
- 制作数据集:
cd scripts 光盘脚本
bash train_full.sh -m dataset bash train_full.sh -m 数据集
or 或者
bash train_lora.sh -m dataset bash train_lora.sh -m 数据集
or 或者
bash train_ptv2.sh -m dataset bash train_ptv2.sh -m 数据集
您好,请教下,制作数据集这一步是做什么的,数据是在data目录已经放好的吧,用make_data_example.py生成的
bash train_lora.sh -m dataset
from qwen_finetuning.
- 制作数据集:
cd scripts 光盘脚本
bash train_full.sh -m dataset bash train_full.sh -m 数据集
or 或者
bash train_lora.sh -m dataset bash train_lora.sh -m 数据集
or 或者
bash train_ptv2.sh -m dataset bash train_ptv2.sh -m 数据集您好,请教下,制作数据集这一步是做什么的,数据是在data目录已经放好的吧,用make_data_example.py生成的
bash train_lora.sh -m dataset
读取配置文件train_pl.yaml 里面的max_length 等信息 制作ids数据集。
from qwen_finetuning.
Related Issues (14)
- infer.py推理异常 HOT 1
- 当batchsize>1 显示shape '[batchsize, -1]' is invalid for input of attention_mask size HOT 1
- int4量化模型transformers使用报错 HOT 2
- lora推理报错 HOT 1
- 重新拉取了最新的Qwen-chat的所有模型和配置,以及本项目的最新代码,无法进行lora微调了 HOT 3
- 有报错,貌似没有设置eos_token HOT 2
- deep_training 这个包里报错 。挺奇怪。 HOT 15
- NN_DataHelper HOT 4
- 反序列化遇到问题 HOT 2
- attention_mask有bug HOT 7
- 请教关于<|endoftext|>的问题 HOT 6
- 请问system 的 prompt为啥固定为 You are a helpful assistant. HOT 2
- 你好,请教下,bash train_full.sh -m train微调后的last.ckpt模型,有办法转成类似https://huggingface.co/Qwen/Qwen-1_8B-Chat/tree/main下面的safetensors文件吗 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 qwen_finetuning.