Comments (3)
Essentially, for any of the fine-tuning data with a custom system prompt, it was not adding it, nor was it prefixing the instructions with USER:. It still worked moderately well, surprisingly, but the training code has been fixed.
I have occasionally noticed blank responses as well, not entirely sure what the cause is yet.
The new versions are here:
- normal: https://huggingface.co/jondurbin/airoboros-c34b-2.2
- de-censored: https://huggingface.co/jondurbin/spicyboros-c34b-2.2
Be sure to update your prompt formatting to use newlines (if you are using the standard USER/ASSISTANT style):
A chat.
USER: {prompt}
ASSISTANT:
No newline or space after "ASSISTANT:"
from airoboros.
Thanks. Not sure how I both searched and missed this apparently multiple times today. Will try again with the new files and verify my prompt.
from airoboros.
Thanks, 2.2 seems to work significantly better. I've converted/uploaded it in EXL2 format too - https://huggingface.co/JorritJ/spicyboros-c34b-2.2-4.0bpw-h6-exl2 .
It still sometimes refuses to give anything but a blank answer. If anyone ever figures out why that is, I'd be happy to learn.
from airoboros.
Related Issues (20)
- Requesting some flexibility in topic input HOT 4
- generating clinically related multiple choice question? HOT 1
- How much resource it took to fine tune llama7/13/70b? HOT 1
- Airoboros 2.0 has difficulty with OOC requests. HOT 3
- what is the prompt template? HOT 1
- [SUGGESTION] (for v2.1+) Classifier-free guidance HOT 1
- how to avoid generating "general" instructions? HOT 1
- Question about learning rate and epochs HOT 4
- [Question] How to create instruction datasets based on domain specific information. HOT 2
- [QUALITY] (Ycros Airoboros v1.4.1 L1-33b 16k) - Hallucinated numbers and narrative. HOT 5
- How can I help? HOT 6
- Overview of the LMoe Process HOT 2
- Speculative sampling and Llmoe? HOT 2
- Break their nasty spines please or what is the point? Also maybe an improvement in the PS HOT 1
- Finetune in INSTRUCT format
- instructiors -> awareness bug? HOT 1
- Add support to Assistant API so Airoboros can use up-to-date data (via search tool) for creating datasets? HOT 1
- LoraAlpha less then LoraRank HOT 2
- Expanding Instruction Complexity with Evol-instruct-like Approaches?
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 airoboros.