Nikityyy / lilleLinks
A powerful 130-million-parameter model trained from scratch as part of a truly open-source stack, including a custom tokenizer, dataset, and optimizer.
☆69Updated 4 months ago
Alternatives and similar repositories for lille
Users that are interested in lille are comparing it to the libraries listed below
Sorting:
- ☆111Updated 7 months ago
- GRadient-INformed MoE☆264Updated last year
- Video+code lecture on building nanoGPT from scratch☆68Updated last year
- Testing LLM reasoning abilities with family relationship quizzes.☆63Updated last year
- A little(lil) Language Model (LM). A tiny reproduction of LLaMA 3's model architecture.☆55Updated 9 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆347Updated last year
- ☆124Updated 7 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆86Updated last year
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆48Updated 3 months ago
- Live-bending a foundation model’s output at neural network level.☆273Updated 9 months ago
- ☆137Updated last year
- Mistral7B playing DOOM☆139Updated last year
- Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLM…☆85Updated last month
- Implementation snake game based on Diffusion model☆93Updated last year
- ☆108Updated 2 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Updated 3 weeks ago
- ☆182Updated 2 months ago
- ☆159Updated 9 months ago
- AI management tool☆119Updated last year
- ~950 line, minimal, extensible LLM inference engine built from scratch.☆405Updated 3 weeks ago
- Pivotal Token Search☆144Updated last month
- Sparse Inferencing for transformer based LLMs☆218Updated 5 months ago
- look how they massacred my boy☆63Updated last year
- Clue inspired puzzles for testing LLM deduction abilities☆45Updated 10 months ago
- AnyModal is a Flexible Multimodal Language Model Framework for PyTorch☆103Updated last year
- A pipeline parallel training script for LLMs.☆166Updated 9 months ago
- An introduction to LLM Sampling☆79Updated last year
- smolLM with Entropix sampler on pytorch☆149Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆61Updated last year
- A character-level language diffusion model trained on Tiny Shakespeare☆842Updated 2 weeks ago