Comments (1)
For the original instruct models they seem to have the wrong end of sentence token specified. You can run mlx lm with the flag --eos-token <|eot_id|>
. Or you can use the quantized models in the HF MLX Community. Those should have the right end of sentence token. If they don't let us know and we will fix.
from mlx.
Related Issues (20)
- [Feature] Build flag to make safetensor and GGUF dependencies optional
- [Feature] something like `mlx.scipy.stats` HOT 2
- [BUG] Passing `axis=None` into `argpartition` causes `TypeError` HOT 1
- [BUG] AttributeError in mlx.core.conj and mlx.core.conjugate functions HOT 3
- Optimization Plans for Conv2D CPU Execution HOT 3
- [BUG] mlx gets stuck with high-dimensional array on Linux HOT 1
- Implement trace analogical to numpy.trace HOT 1
- [BUG] Wrong slice of a 4D array assigned to with GPU HOT 1
- problem of using mlx package HOT 2
- Question about supporting slices of the type a[:, [0]] HOT 2
- Difference in training convergence between PyTorch & MLX HOT 2
- [BUG] mlx.core.topk throws segmentation fault for large dimension HOT 1
- [BUG] JIT compile mode does not work with LoRA
- [Feature] dlpack device HOT 5
- [BUG] Compiled mx.eval(model.state) raises “Attempting to eval an array without a primitive” with mlx.optimizers.Adam HOT 4
- [BUG] compile + checkpoint segfaults HOT 1
- [BUG] Wrong result for sliced matmul on GPU HOT 1
- I'm asking for help with the following error: HOT 1
- [Enhancement] be able to override MLX_METAL_VERSION when running cmake
- Potential mx.load() issue with quantized GGUF's HOT 1
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.