Comments (3)
是的 这两个参数名有点confusing,我回头改一下
from anima.
另外,我看到计算loss的时候,是把prompt + query + response都算上了,为什么呢?我们以为只要算response的loss,。
from anima.
另外,我看到计算loss的时候,是把prompt + query + response都算上了,为什么呢?我们以为只要算response的loss,。
这个大部分情况对performance影响不大。回头我可以加一个参数可以disable instruction。
from anima.
Related Issues (20)
- dpo+lora训练llama2 70B失败
- qwen报错 HOT 11
- Provide minimum required versions HOT 1
- internlm-chat-20b模型剪枝失败 HOT 2
- ValueError: max() arg is an empty sequence HOT 1
- Question on inference run time.
- Error on first run HOT 2
- AirLLMLlama2 error: TypeError: llama_forward() got an unexpected keyword argument 'padding_mask' HOT 4
- 外推训练时max-position-embeddings需要做调整吗? HOT 1
- So much time loading HOT 1
- Support for T5 based models
- cant initial NVML HOT 2
- cant initial NVML.... No CUDA GPUs are available HOT 4
- RuntimeError: expected scalar type struct c10::Half but found double HOT 2
- ImportError: cannot import name 'AirLLMLlama2' from partially initialized module 'airllm' (most likely due to a circular import) HOT 1
- Running the example inference code and I get error HOT 3
- Mistral Model ValueError: Asking to pad but the tokenizer does not have a padding token HOT 2
- airllm是否支持ptunig、lora等微调模型的加载?
- [Feature Request] Mixtral Model Support HOT 11
- what's the difference or advantage of airllm vs flexgen?
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 anima.