A small language model you train yourself. Character-level transformer built from scratch in PyTorch, exported a quantized compressed text file that runs anywhere.
-
Updated
Sep 14, 2026 - Python
#
slm-training
Here are 2 public repositories matching this topic...
Universal Framework for Memory Decoder (2025) Training (optimized for compact SLMs, CPU & Low GPU for Local AI)
text-generation domain-adaptation local-first end-to-end-pipeline cpu-optimized local-llm llm-inference local-ai llm-finetuning small-language-models unsloth gemma3 rag-alternative smollm3 qwen3-5 cpu-gpu-hybrid slm-training
-
Updated
Oct 10, 2026 - Python
Add this topic to your repo
To associate your repository with the slm-training topic, visit your repo's landing page and select "manage topics."