dmf-archive / PILFLinks
PILF: A IPWT-inspired bionic continual learning experiment focus on mitigate catastrophic forgetting with Surprise-gated Mixture of Experts (MoE) model.
☆38Updated 6 months ago
Alternatives and similar repositories for PILF
Users that are interested in PILF are comparing it to the libraries listed below
Sorting:
- A playground to make it easy to try crazy things☆33Updated last month
- Hierarchical topic segmentation of meeting transcripts using embeddings and divisive clustering.☆54Updated last year
- Pivotal Token Search☆142Updated last month
- Information Processing Evaluation for Large Language Models☆34Updated last month
- Dead Simple LLM Abliteration☆246Updated 11 months ago
- A star for organising blocks and playing with transformers.☆23Updated last year
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆125Updated 9 months ago
- Your AI research assistant☆79Updated 9 months ago
- ☆200Updated 8 months ago
- Build data processing and data analysis pipelines that leverage the power of LLMs 🧠☆246Updated last month
- Testing platform for covert data exfiltration techniques where sensitive documents are embedded into vector representations and tunneled …☆67Updated 5 months ago
- A library for reproducible deep learning.☆83Updated last month
- Implement recursion using English as the programming language and an LLM as the runtime.☆239Updated 2 years ago
- A library for incremental loading of large PyTorch checkpoints☆56Updated 2 years ago
- Visual inference exploration & experimentation playground☆97Updated last year
- Your appetite for code + Claude's capabilities = Limitless creation. No experience required - just pure hunger! 🧠⚡💻☆58Updated 7 months ago
- A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advan…☆29Updated 9 months ago
- ☆69Updated 3 months ago
- Heirarchical Navigable Small Worlds☆101Updated 5 months ago
- This is a framework that implements various parallel reasoning strategies from the literature☆275Updated last month
- ☆253Updated 10 months ago
- Neurox control helm chart details☆30Updated 8 months ago
- Analyzing hacker news in real-time with Bytewax and Proton☆44Updated last year
- Live-bending a foundation model’s output at neural network level.☆272Updated 9 months ago
- ~ streaming agents☆74Updated 3 weeks ago
- A notebook that compares a reasoning model x a non reasoning model that runs a loop using logprobs found uncertainty☆25Updated 5 months ago
- A CLI to manage install and configure llama inference implemenation in multiple languages☆65Updated 2 years ago
- LLM plugin for pulling content from Hacker News☆124Updated 8 months ago
- Editor with LLM generation tree exploration☆81Updated 11 months ago
- ☆164Updated 9 months ago