okarthikb / attention-visualizer
LLM attention pattern visualizer
☆10Updated last year
Alternatives and similar repositories for attention-visualizer:
Users that are interested in attention-visualizer are comparing it to the libraries listed below
- Collection of autoregressive model implementation☆85Updated 2 months ago
- Jax like function transformation engine but micro, microjax☆30Updated 6 months ago
- ☆27Updated 9 months ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆28Updated this week
- ☆49Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- ☆14Updated last year
- Minimum Description Length probing for neural network representations☆19Updated 2 months ago
- Low-Rank Adaptation of Large Language Models clean implementation☆8Updated last year
- ☆22Updated last year
- ☆28Updated 5 months ago
- MEXMA: Token-level objectives improve sentence representations☆40Updated 3 months ago
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆14Updated last year
- An introduction to LLM Sampling☆77Updated 4 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 7 months ago
- ☆24Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆29Updated last month
- ☆78Updated 8 months ago
- ☆21Updated 4 months ago
- Train, tune, and infer Bamba model☆88Updated this week
- Measuring and Controlling Persona Drift in Language Model Dialogs☆17Updated last year
- Training hybrid models for dummies.☆20Updated 3 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆62Updated this week
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆30Updated last month
- Shakespeare transformer fine-tuned to generate positive sentiment samples using RLHF☆10Updated 2 years ago
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆43Updated last year
- See https://github.com/cuda-mode/triton-index/ instead!☆11Updated 11 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated last month
- FBI: Finding Blindspots in LLM Evaluations with Interpretable Checklists☆28Updated last month