Skip to content
#

cpu-native

Star

Here are 4 public repositories matching this topic...

Language: All
Filter by language
All 4 Python 3 HTML 1

tgakathunderr / BIM-2

Star 22

Biologically inspired language model using Jaccard Surprise as its only training signal. No backprop. No GPU. Online Hebbian learning from corrections. Two-layer cortex with apical feedback. Runs on CPU under 200MB.

python machine-learning ai artificial-intelligence computational-neuroscience artificial-neural-networks neuromorphic htm jaccard hebbian-learning online-learning cortical-learning sparse-distributed-representations cpu-native lightweight-ai biologically-inspired no-backpropagation
  • Updated May 21, 2026
  • Python
cpu-native-lm-train

shyringo / cpu-native-lm-train

Star 0

34.1M LM on a laptop CPU: 215,771 tok/s, 8,529x Qwen. QSELM beats Qwen3.5-0.8B on sealed long-document QA (90.6% vs 45.8%) and Qwen3-0.6B-FC on cross-turn agent memory (69.6% vs 3.2%). No GPU. | 笔记本CPU训练34.1M模型：21.6万token/s，实测为Qwen的8,529倍；长文档问答，QSELM 90.6%，Qwen3.5-0.8B 45.8%；Agent跨轮次记忆，QSELM 69.6%，Qwen3-0.6B-FC 3.2%；无需GPU。

nlp training machine-learning cpu inference text-generation language-model sparse-learning tool-use cpu-training llm function-calling local-ai cpu-native agent-memory qselm
  • Updated Aug 25, 2026
  • Python

Improve this page

Add a description, image, and links to the cpu-native topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the cpu-native topic, visit your repo's landing page and select "manage topics."

Learn more