Comments (3)
Thanks for reporting. It's not necessarily a bug but more like a hard-coded sanity check. It's to check that the LLM can generate coherent text. We can replace this with a concrete example from the validation set though. I think some other users asked for that a while ago as well.
from litgpt.
Yes please do that it would be really helpful. Or you can add an argument that allow us to select whether we want to see validation output for "recommend a movie" or response to our own dataset. Thanks!
from litgpt.
Let me reopen that so I don't forget to add it :)
from litgpt.
Related Issues (20)
- API has confusing/wrong description HOT 1
- Set kv cache size based on resource needs
- Pretrain then finetune on multiple GPUs error
- adding Aya model (checkpoints) to the supported checkpoints list that litgpt support
- did not convert the model to litgpt format, why? HOT 3
- Support downloading and using quantized weights (GGUF)
- Autodownload + conversion now fails on the first try
- Skip safetensors->bin file conversion
- Mistral Large 2 Checkpoints HOT 1
- Support sequential generation in litgpt serve HOT 1
- Provide minimal installation
- Implement prompt caching to speed up inference HOT 1
- access hidden layer(s) from a model
- TPU Pod Training
- MPS test gave out gibberish result HOT 3
- Use FlexAttention
- Tensor parallelism generates non-sensical outputs HOT 1
- Gemma 2B weights seem to have changed HOT 1
- Disable KV cache option
- attention mask is incorrect when generate with softcapping HOT 8
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 litgpt.