goodfire-ai / sdxl-turbo-interpretabilityLinks
☆42Updated 2 months ago
Alternatives and similar repositories for sdxl-turbo-interpretability
Users that are interested in sdxl-turbo-interpretability are comparing it to the libraries listed below
Sorting:
- Plotting (entropy, varentropy) for small LMs☆98Updated 2 months ago
- Simple Transformer in Jax☆138Updated last year
- look how they massacred my boy☆63Updated 9 months ago
- Sparse autoencoders for Contra text embedding models☆25Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆103Updated 5 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- Cerule - A Tiny Mighty Vision Model☆66Updated 11 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated 9 months ago
- ☆38Updated last year
- smolLM with Entropix sampler on pytorch☆150Updated 9 months ago
- WIP☆94Updated 11 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆99Updated 3 weeks ago
- train entropix like a champ!☆19Updated 9 months ago
- An introduction to LLM Sampling☆79Updated 7 months ago
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- A toy Inspect implementation of the Bliss Attractor eval from Claude 4 System Card Welfare Assessment☆26Updated 2 months ago
- SIMD quantization kernels☆78Updated this week
- A simple script to see how my ideas evolve over time☆42Updated 2 months ago
- A graph visualization of attention☆57Updated 2 months ago
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆33Updated 5 months ago
- ☆30Updated 10 months ago
- σ-GPT: A New Approach to Autoregressive Models☆67Updated 11 months ago
- H-Net Dynamic Hierarchical Architecture☆65Updated 2 weeks ago
- Gradient descent is cool and all, but what if we could delete it?☆104Updated this week
- Lego for GRPO☆28Updated 2 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 6 months ago
- Applying SAEs for fine-grained control☆23Updated 7 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 9 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆69Updated 3 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 5 months ago