Comments (4)
both of them cannot get the results as expected
Either approach is quite reasonable and should work. What happens when you try?
from mlx-examples.
both of them cannot get the results as expected
Either approach is quite reasonable and should work. What happens when you try?
I suspect it is due to the contents of training datasets, should I need to involve some datas from the previous training datasets into the new one?
I just did some evaluation for incremental LoRA fine-tuning, so I put the same contents from train.jsonl into the valid.jsonl for the new training datasets, Is it right?
from mlx-examples.
both of them cannot get the results as expected
Either approach is quite reasonable and should work. What happens when you try?
For example I use with fused only for Q "who are the members of *** team?", Answer is perfect.
After adding some new training datasets, I use the fused model with the new adapters.npz, Q "who are the members
of *** team?", the answer contains some people names from the new training sets, but these names are from totally different questions of new datasets.
If I combine the old and new datasets into only a train.jsonl and valid.jsonl, do the LoRA training from the scratch , the result is as expected.
I use Chinese characters in training datasets.
from mlx-examples.
@southkorea2013 did you ever try mixing old data with new data? I think that should probably solve your issue. I'm closing this as it's not really a bug / specific request. If you want to start a discussion about please go ahead.
from mlx-examples.
Related Issues (20)
- [Feature Request] MLX_lm: Store KV cache of computed prompts to disk to avoid re-compute in follow-up runs HOT 1
- ValueError: "DoRALinear does not yet support quantization" after DoRA fine-tuning HOT 1
- Support example for SpeechT5 model?
- Feature Request: Implement Tool Calling for llama-3.1 in MLX-LM HOT 3
- Example of an async data-loader that automatically pre-fetches batches for training HOT 1
- How to use the Apple Neural Engine with MLX? HOT 1
- mlx_lm.fuse raises RuntimeError: std::bad_cast HOT 1
- [FeatureRequest] Support Qwen2-Audio model
- Optimal way of accumulating gradients? HOT 2
- [FeatureRequest] Support for prompt fine-tuning
- MLX_lm:generate() or stream_generate() how to setting system prompt and model config? HOT 2
- Generation fails after quantization for multi-part models HOT 4
- Update whisper/convert.py to save as safetensors instead of npz
- Performance tracing and tuning code
- "Warning: 'Example already has an EOS token appended' and Increased Memory Usage with Mistral Nemo Model" HOT 6
- Mlx generate text, by default halusonates more HOT 3
- `trust_remote_code` needed to convert InternLM-2.5 20b model HOT 2
- MNIST test accuracies differ drastically with --gpu flag on and off on Apple M3 HOT 2
- [Feature Request] MLX_lm: add support for GLM4 family of language models
- Weird text generation with llama.py
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 mlx-examples.