Comments (6)
Please first check if the original model can infer properly before training. Then check the log and GPU status when do inference process by the way.
My System is "win11, python 3.10, RTX 4090 , pytorch 2.1.2, Llama Factory 0.6.3", which is OK for both Llama2 and Llama3.
Bless!
from llama-factory.
Llama-3 model can generate texts in our Linux environment. I think it is likely an issue with your hardware and environment.
from llama-factory.
Llama-3 model can generate texts in our Linux environment. I think it is likely an issue with your hardware and environment.
``
from llama-factory.
I'm using the Smaller Llama3 model, I'm not trying to train on the larger 70b model. I'm on a 3090 rtx gpu, on windows, is windows ok? I'm not sure I'd be able to get this running on Linux... maybe I need to though.
I has WSL for windows to install stuff but I'm so new to it I have no idea how I'd get started
from llama-factory.
Please first check if the original model can infer properly before training. Then check the log and GPU status when do inference process by the way. My System is "win11, python 3.10, RTX 4090 , pytorch 2.1.2, Llama Factory 0.6.3", which is OK for both Llama2 and Llama3.
Bless!
windows is ok. please do more environment check and try the official inference demo of llama3 which is in https://huggingface.co/blog/llama3.
bless.
from llama-factory.
Please first check if the original model can infer properly before training. Then check the log and GPU status when do inference process by the way. My System is "win11, python 3.10, RTX 4090 , pytorch 2.1.2, Llama Factory 0.6.3", which is OK for both Llama2 and Llama3.
Updating pytorch from 2.0.2 to 2.1.1 resolved my problem.
from llama-factory.
Related Issues (20)
- dpo单机多卡 HOT 1
- Reward model prediction problem HOT 1
- 建议 自定义的数据集,或者数据集定义这部分放在训练文件中,避免打包镜像后,训练自定义数据到时候还需要修改公共文件
- 有多机多卡训练llama3-70b的参考程序吗? HOT 1
- Warning: Non finite check and unscale on NPU device! 昇腾卡上训练 HOT 1
- 如果用户的一句message包含多个Function Call name,自带的推理代码是否支持识别 HOT 1
- dpo全参微调后,预测时无法加载权重文件 HOT 3
- 【HELP】如何SFT的时候取消某个模型的默认system prompt,是否有一些命令可以指定 HOT 1
- 使用 TPU 训练 ERROR: Unknown command line flag 'xla_latency_hiding_scheduler_rerun' HOT 1
- 训练PPO时,--adapter_name_or_path 指向sft模型 --reward_model 指向奖励模型 HOT 1
- 如何修改tokenizer读取目录 HOT 1
- 會增加SimPO算法嗎? HOT 1
- 启动val=0.1评估的时候,每次用于评估的数据是否会改变。 HOT 1
- PPO一直提示KL散度为负。 HOT 2
- 2卡A40lora微调qwen报错TypeError: Input weight should be of type nn.Parameter, got <class 'torch.Tensor'> instead HOT 2
- 如何使用命令行版本 HOT 1
- qwen1.5 chat_template 问题
- 用于每一步训练的数据是不是存放在这个训练的数据加载器中 train_dataloader = trainer.get_train_dataloader() HOT 1
- fsdp_qlora fail HOT 5
- 预训练codeqwen1.5-7b时显存分布异常,训练一段时间后爆OOM HOT 4
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.