r-three / git-thetaLinks
git extension for {collaborative, communal, continual} model development
☆213Updated 7 months ago
Alternatives and similar repositories for git-theta
Users that are interested in git-theta are comparing it to the libraries listed below
Sorting:
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆208Updated 2 weeks ago
- Erasing concepts from neural representations with provable guarantees☆228Updated 4 months ago
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆257Updated last year
- An interactive exploration of Transformer programming.☆264Updated last year
- ☆92Updated last year
- ☆303Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- ☆67Updated 2 years ago
- Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)☆310Updated 2 years ago
- Train very large language models in Jax.☆204Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- A puzzle to learn about prompting☆128Updated 2 years ago
- ☆60Updated 3 years ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆134Updated this week
- Amos optimizer with JEstimator lib.☆82Updated last year
- ☆166Updated last year
- ☆134Updated 2 months ago
- Fast bare-bones BPE for modern tokenizer training☆159Updated 2 months ago
- nanoGPT-like codebase for LLM training☆98Updated last month
- Named tensors with first-class dimensions for PyTorch☆331Updated 2 years ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆309Updated 2 years ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆595Updated this week
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes☆239Updated 2 years ago
- Automatic gradient descent☆208Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆206Updated last week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆127Updated last year
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆82Updated last year