Comments (6)
This issue is marked as stale because it has been marked as invalid or awaiting response for 7 days without any further response. It will be closed in 7 days if the stale label is not removed or if there is no further response.
from internlm.
@zhangxc11 @lvhan028 @sunpengsdu @gouchangjiang 您们好, 能回答一下这个问题吗? 谢谢!
from internlm.
Hi, @timousT 抱歉回复晚了。
关于使用 xtuner 的微调,@pppppM 更清楚些。我请他来回复下
from internlm.
@timousT 如果想用 XTuner 进行扩词表训练,可以按以下步骤进行
- 挑选对应模型的 config 模板
xtuner list-cfg -p internlm2
xtuner copy-cfg internlm2_chat_7b_qlora_alpaca_e3 ./internlm2_chat_7b_new_tokenzier_alpaca_e3.py
-
在 config 中设置扩词表后的 tokenizer
vi internlm2_chat_7b_new_tokenzier_alpaca_e3.py
https://github.com/InternLM/xtuner/blob/56dbdd7610f99c5cd22c7fa59846fe46906370f7/xtuner/configs/internlm/internlm2_chat_7b/internlm2_chat_7b_qlora_alpaca_e3.py#L63 -
使用全参数微调
XTuner 默认使用 QLoRA 进行微调,不会训练 embbeding 和最后的 fc
只需要将 config 中的quantization_config
和lora
删掉即可
vi internlm2_chat_7b_new_tokenzier_alpaca_e3.py
https://github.com/InternLM/xtuner/blob/main/xtuner/configs/internlm/internlm2_chat_7b/internlm2_chat_7b_qlora_alpaca_e3.py#L75-L90 -
使用 DeepSpeed 启动训练
`xtuner train internlm2_chat_7b_new_tokenzier_alpaca_e3.py --deepspeed_deepspeed_zero3
如果想训练自己的数据,可以参考 XTuner 文档准备数据集
https://github.com/InternLM/xtuner/blob/main/docs/zh_cn/user_guides/multi_turn_conversation.md
from internlm.
This issue is marked as stale because it has been marked as invalid or awaiting response for 7 days without any further response. It will be closed in 7 days if the stale label is not removed or if there is no further response.
from internlm.
This issue is closed because it has been stale for 7 days. Please open a new issue if you have similar issues or you have any new updates now.
from internlm.
Related Issues (20)
- [QA] 书生2模型有关chat_template的问题 HOT 5
- [Bug] 微调eval阶段使用generate的结果会出现</s> HOT 2
- 请问是否支持200k上文的微调,需要什么样的配置?[QA] HOT 2
- [Bug] InternLM2 int4 出现重复说话、重复前置内容(system prompt)现象 HOT 9
- [Bug] When loading a model by using transformers and using stream chat, it seems no whitespace character in English response. HOT 1
- [QA] Number of training tokens for Internlm2 1.8B, 7B, and 20B? HOT 3
- [QA] 请问是否会开源PPO的训练code和reward model? HOT 1
- [Feature] 是否已经支持tensorrt-llm或者计划支持? HOT 2
- [Bug] Special tokens are still mismatched. HOT 2
- [Bug] internlm2-chat-20b huggingface下载503报错,模型不存在
- 一人血书求讲解怎么来洗数据! HOT 5
- 万人血书 InternLM2-4B ❗❕❗❕❗
- [QA] Can internlm2 be supported in fastchat? HOT 6
- [Bug] failing everytime and getting CUDA out of memory HOT 6
- [Bug] internlm2_chat_1.8b 模型不支持多轮对话 HOT 2
- [QA] 使用InternLM微调qa机器人,如何让它从训练资料中选择答案,而不是自己生成? HOT 2
- [Feature] convert2llama.py HOT 1
- [Bug] safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge HOT 3
- [QA] Question about phase 2 long context pretraining batch size HOT 3
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 internlm.