srush / GPTWorldLinks
A puzzle to learn about prompting
☆127Updated 2 years ago
Alternatives and similar repositories for GPTWorld
Users that are interested in GPTWorld are comparing it to the libraries listed below
Sorting:
- Puzzles for exploring transformers☆347Updated 2 years ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- An interactive exploration of Transformer programming.☆264Updated last year
- Simple Transformer in Jax☆137Updated 11 months ago
- Understand and test language model architectures on synthetic tasks.☆197Updated 2 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆127Updated last year
- Draw more samples☆191Updated 11 months ago
- ☆433Updated 7 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆214Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆116Updated 5 months ago
- RuLES: a benchmark for evaluating rule-following in language models☆224Updated 3 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆169Updated this week
- Repository for the paper Stream of Search: Learning to Search in Language☆147Updated 4 months ago
- ☆78Updated 11 months ago
- JAX implementation of the Llama 2 model☆217Updated last year
- seqax = sequence modeling + JAX☆155Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆128Updated 3 weeks ago
- Fast bare-bones BPE for modern tokenizer training☆157Updated 2 months ago
- Website for hosting the Open Foundation Models Cheat Sheet.☆267Updated 3 weeks ago
- Resources from the EleutherAI Math Reading Group☆53Updated 3 months ago
- ☆182Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Erasing concepts from neural representations with provable guarantees☆228Updated 4 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 4 months ago
- A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).☆147Updated 5 months ago
- ☆267Updated 10 months ago
- git extension for {collaborative, communal, continual} model development☆212Updated 6 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆100Updated 2 months ago