Comments (3)
awni
commented on June 28, 2024
1
Not sure, but possibly due to using too much RAM to remap weights. Try requantizing locally or use https://huggingface.co/mlx-community/Mixtral-8x22B-Instruct-v0.1-4bit. I am in the process of requantizing and uploading, should be done within an hour.
from mlx-examples.
kaandedeoglu
commented on June 28, 2024
Makes sense - we have quantized the model with an older version of MLX around a few days after the model's release (April 17 2024)
from mlx-examples.
awni
commented on June 28, 2024
This was resolved by reboot. I think the underlying issue of memory fragmentation / some kind of perf regression in the OS for M2 Ultra is still there. I'm fairly certain this issue is a dup of #776. I will follow up on 776 with any improvements related to this problem.
from mlx-examples.
Related Issues (20)
- CLIP Tokenizer unable to take text of unequal length (or token length) HOT 7
- Package 'mlx_whisper.assets' is absent from the `packages` configuration HOT 1
- [Feature Request] Add support for logprobs to the mlx_lm server HOT 3
- Request for Example on Full Parameter and Training for LLM Model HOT 5
- Phi-3 128K Context Variants' `su` RoPE Scaling HOT 12
- I would like to inquire about a solution to the following problem. HOT 1
- link to Phi-2 example in readme broken HOT 1
- SPMStreamingDetokenizer sometimes outputs incorrect multi-byte characters HOT 1
- Why change the module decomposition of whisper HOT 3
- A simple enhancement, in dataset creation time HOT 1
- [Question]about creating the 'adapters.npz' file HOT 3
- [QUESTION] Is there a way to provide a Huggingface access token for downloading models that are private? HOT 1
- [Model Request] Add support for IBM's Granite model HOT 2
- [Feature] Export Lora Adapters as GGML HOT 3
- Error when running inference on newly converted OpenELM MLX model, ValueError(f"Received parameters not in model: {extras}.") HOT 1
- LLMEvaluator : libc++abi: terminating due to uncaught exception of type std::invalid_argument: [matmul] Last dimension of first input with shape (1,916,2048) must match second to last dimension of second input with shape (256,32000)
- Unable to allocate memory
- Proposal: Add mypy to .pre-commit-config.yml HOT 2
- Fusing adapters with llama3 cause bad performances HOT 3
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.