Downloads · 30 days
9
26% of all-time downloads
bradeenl/cwm-q6-mlx
cwm-q6-mlx is a machine learning model from bradeenl. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as fair-noncommercial-research-license.
This repository contains the MLX conversion of CWM with an 6bit quantization.
Downloads · 30 days
9
26% of all-time downloads
All-time downloads
35
Public
Parameters
32.6B
26.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors26.5 GB · 100%
How the weights are stored.
U326.1B · 86%
From the Hugging Face model README
This repository contains the MLX conversion of CWM with an 6bit quantization.
mlx_lm.generate --model . --prompt "hello"
==========
Okay, the user just said "hello". I need to respond in a friendly way. Maybe I can ask how they're doing or if there's something I can help them with. Let me think of a few options. I could say "Hello! How are you today?" or "Hi! Is there something I can help you with?" or maybe just "Hi! What's up?" I should choose something that's welcoming and shows I'm ready to chat.
</think>
Hello! How
==========
Prompt: 14 tokens, 16.935 tokens-per-sec
Generation: 100 tokens, 12.865 tokens-per-sec
Peak memory: 26.551 GB