Comments (4)
CUDA_VISIBLE_DEVICES=1 python3 uniform_finetune.py --model_type chatglm --model_name_or_path huggingface.co/THUDM/chatglm3-6b --data ./data/formatted_cot_data/aqua_train.json ./data/formatted_cot_data/ecqa_train.json ./data/formatted_cot_data/esnli_train.json --lora_target_modules query_key_value --lora_r 32 --lora_alpha 32 --lora_dropout 0.1
运行uniform_finetune.py这个脚本进行进行微调,出现了
这个问题。
使用的数据是库中自带的几个jsno数据
from alpaca-cot.
【1】 其实3是可有可无的一步,在1微调得到lora权重后,2inference时同时加载llm和lora的权重即可完成推理。而3则是将lora合进llm的操作,用lora替代原有llm中的矩阵,得到一个新的llm,可直接用新llm完成推理,不再需要同时再加载llm和lora权重了。因此3并不是一个必要操作,基本上1和2就满足了训练和测试的需求。
【2】用uniform_finetune.py跑llama-13应该是能跑起来的,是不是本地显存过低?
【3】tabular_LLM主要是提供了相关tabular数据,模型训练相关的代码请参考main分支。
from alpaca-cot.
CUDA_VISIBLE_DEVICES=1 python3 uniform_finetune.py --model_type chatglm --model_name_or_path huggingface.co/THUDM/chatglm3-6b --data ./data/formatted_cot_data/aqua_train.json ./data/formatted_cot_data/ecqa_train.json ./data/formatted_cot_data/esnli_train.json --lora_target_modules query_key_value --lora_r 32 --lora_alpha 32 --lora_dropout 0.1
运行uniform_finetune.py这个脚本进行进行微调,出现了 这个问题。 使用的数据是库中自带的几个jsno数据
暂时还不支持chatglm3 可以跑下chatglm2就不会有这个报错了
from alpaca-cot.
CUDA_VISIBLE_DEVICES=1 python3 uniform_finetune.py --model_type chatglm --model_name_or_path huggingface.co/THUDM/chatglm3-6b --data ./data/formatted_cot_data/aqua_train.json ./data/formatted_cot_data/ecqa_train.json ./data/formatted_cot_data/esnli_train.json --lora_target_modules query_key_value --lora_r 32 --lora_alpha 32 --lora_dropout 0.1
运行uniform_finetune.py这个脚本进行进行微调,出现了 这个问题。 使用的数据是库中自带的几个jsno数据暂时还不支持chatglm3 可以跑下chatglm2就不会有这个报错了
好的,我试一下2
from alpaca-cot.
Related Issues (20)
- ChatGLM的Finetune推荐命令,使用3090 24G会OOM,代码默认使用8Bit量化同样会导致OOM HOT 1
- 请问如何修改模型的自我认知
- GPTeacher Code-Instruct HOT 1
- 8卡V100跑moss OOV HOT 2
- Prompt设置 HOT 1
- About the tokenizer
- The text meaning in zh_helpfulness_context.json in Alpaca-CoT / MOSS / moss-002-sft
- DataCollatorForLanguageModeling uses the unmasked labels
- web.py中缺少--size参数 HOT 1
- inference结果差异比较大,请问是什么原因 HOT 2
- 是否可以提供一个Gdrive和百度云的下载方式 HOT 2
- 是否可以支持qlora
- 你好,群二维码过期了 HOT 1
- About the source of the dataset
- What is the relationship between the data and the link you provided?
- 你好,能更新下群信息么 HOT 2
- Adding Contributors Section In readme.md
- 你好,群二维码过期了,能更新一下么~ HOT 6
- 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 alpaca-cot.