Comments (6)
- The repo show how to test the throughput.
- This project is now just used for the train, the inference's implementation will be added later(the main branch's inference just for test).
from mlora.
Thanks for replying to me.
Yes, I understand the patch.
I just got confused by the feed-forward part in the tuning session,
aren't we supposed to do auto-regression in the feed-forward parts?
from mlora.
Do you mean why there is only use the output to train, not like the inference produces token by token and calc the MSELoss?
from mlora.
Yes,
I was thinking aren't we supposed to first generate a series of outputs and then use the output tokens to compare with the ground truth label?
Like: "ML is Fun" as input, Out put is "ML is Fun topic to work on" which add 4 words(maybe 12 tokens)
Then the ground truth is "ML is Fun topic indeed"
Then we compare these two.
from mlora.
I think sequence classification/regression does this, if we just train for chat, cross-entropy loss maybe better.
If your input is "ML is Fun topic indeed.", the output will contain all sub-sequence predictions, "ML xx", "ML is xx", "ML is Fun xx", "ML is Fun topic xx". Then we calc the cross-entropy loss.
But we can add the classification/regression features later if needed.
from mlora.
since no comments, i would like to close this one.
from mlora.
Related Issues (20)
- how to evaluate this model
- How to predict via the command line or webui?
- How to fine tune on one model via different rank ? then output the model best rank?
- provide more dataset to test
- provide the script to prepare the fine tune dataset
- provide more model eval methods
- Log style not consistent
- issue about chatglt model
- Will Embeding change? HOT 4
- Known Issues
- How to use this frame work to train a LLM with multi-GPUs? HOT 7
- About Mix LoRA HOT 2
- Issues about integrated inference
- AttributeError: 'ChatGLMForConditionalGeneration' object has no attribute 'init_lora_weight'
- The MixLoRA (LoRA + MoE) and its related improvements are available at mikecovlee/mlora. HOT 1
- can support llava model ? HOT 3
- ImportError: cannot import name 'override' from 'typing' HOT 2
- plyvel._plyvel.IOError: b'IO error: lock /tmp/mlora/./db/LOCK: Resource temporarily unavailable'
- Support model inference with adapters
- Support automatic parameter configuration
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 mlora.