hallerite / ludicLinks
Ludic – an LLM-RL library for the era of experience
☆37Updated this week
Alternatives and similar repositories for ludic
Users that are interested in ludic are comparing it to the libraries listed below
Sorting:
- look how they massacred my boy☆63Updated last year
- PageRank for LLMs☆51Updated 3 months ago
- ☆71Updated last month
- ☆40Updated last year
- lossily compress representation vectors using product quantization☆59Updated last month
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆99Updated 5 months ago
- Storing long contexts in tiny caches with self-study☆220Updated 2 weeks ago
- Pivotal Token Search☆135Updated this week
- explore token trajectory trees on instruct and base models☆149Updated 6 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 2 months ago
- ☆68Updated 6 months ago
- Approximating the joint distribution of language models via MCTS☆22Updated last year
- Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic in…☆27Updated 6 months ago
- ☆29Updated last month
- Curated collection of community environments☆195Updated this week
- Simple Transformer in Jax☆141Updated last year
- Training code for Sparse Autoencoders on Embedding models☆39Updated 9 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 2 months ago
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated 3 months ago
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?☆228Updated last month
- A framework for optimizing DSPy programs with RL☆298Updated last month
- SIMD quantization kernels☆93Updated 3 months ago
- MoE training for Me and You and maybe other people☆239Updated this week
- ☆14Updated 8 months ago
- a curated list of data for reasoning ai☆140Updated last year
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆125Updated 8 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated last year
- ☆213Updated this week
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 3 months ago
- Super basic implementation (gist-like) of RLMs with REPL environments.☆286Updated 2 months ago