Comments (4)
建议在
修改为
if cast_trainable_params_to_fp32 and is_trainable:
from llama-factory.
推理命令是什么?
from llama-factory.
python src/train.py examples/lora_single_gpu/llama3_lora_predict.yaml
后续我尝试了
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch
--config_file examples/accelerate/single_config.yaml
src/train.py examples/lora_single_gpu/llama3_lora_predict.yaml
虽然input embedding(fp32)和proj weight(fp16)仍然不一致,但是没有报错,可以正常计算
from llama-factory.
已修复
from llama-factory.
Related Issues (20)
- 训练内置数据集c4_demo时报错 HOT 1
- 我在预训练qwen0.5b时想给这个大模型引入新的token
- 在sft训练之后进行合并提示我 Can't find 'adapter_config.json' HOT 1
- openai.NotFoundError: Error code: 404 - {'detail': 'Not Found'}
- 模型导出的问题,路径正确却报错路径不正确
- 一张4090 单卡部署qwen2-7b模型占用了20g显存,而用两张4090卡,每张都会各占20g,而不是每张卡平摊10g呢? HOT 1
- GLM4-9B 推理完后进度条卡在100%需要等到很长时间才会出结果 HOT 1
- lora微调大模型的时候出现了如下报错,请问我该如何修改 HOT 2
- help!数据集导入错误
- 关于使用2张A100去训练qwen2-7b-instruct出问题的情况 HOT 3
- 您好,想请问一下目前有适配fp8的计划吗
- 使用gptq量化的校准数据集格式 HOT 1
- 训练出错,版本v0.8.2 HOT 2
- 如何查看训练.yaml文件中支持的所有参数及每个参数对应的解释 HOT 1
- openai接口中toolcall的响应报文中,丢失tool_call_id字段
- train llama3-8b on wikitext dataset at stage sft HOT 1
- template HOT 1
- 模型结构发生改变后微调报错
- 无法通过pip install -e ".[torch-npu,metrics]"安装
- 导出模型的时候发生了错误
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.