Instructions to use moncefem/memory-lora-gemma4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use moncefem/memory-lora-gemma4 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Commit History
-
Push ALL raw datasets: commitpack (9 langs), RepoPeftBench/code2lora, combined corpora
moncefem +1: Claude Opus 4.8Adds the full raw training corpora (~9.5GB) previously kept local-only. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>cd50fed -
Update aligned6 training dataset to v4 (2066 repos / 27501 QA incl. batch2 novel + enhanced QA)
moncefem +1: Claude Opus 4.8Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>02f08b1 -
8am snapshot: complete ~1650-repo dataset + batch2 novel repos + v3 checkpoints
moncefem +1: Claude Opus 4.8LFS-track data/*.jsonl (multiview_sources grew past 10MB with 2083 repos). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>fb5235a
-
Memory-LoRA hypernetwork for Gemma-4-E2B: code, curated data, sixview checkpoints
moncefem +1: Claude Opus 4.8Hypernetwork that generates repo-specific LoRA adapters for a frozen google/gemma-4-E2B (zero inference-time token overhead). Includes the memory_lora package, all data/build/train/eval scripts, the aligned 6-view dataset, and the sixview_v1/v2 checkpoints. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CeUvTz4vLw4ni2ZNR6pS1p481fbb6