epfml / llm-baselinesLinks
nanoGPT-like codebase for LLM training
โ102Updated 3 months ago
Alternatives and similar repositories for llm-baselines
Users that are interested in llm-baselines are comparing it to the libraries listed below
Sorting:
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ153Updated 2 months ago
- A MAD laboratory to improve AI architecture designs ๐งชโ125Updated 8 months ago
- Understand and test language model architectures on synthetic tasks.โ222Updated last month
- โ53Updated last year
- Language models scale reliably with over-training and on downstream tasksโ98Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"โ81Updated 9 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ191Updated last year
- โ56Updated 10 months ago
- โ81Updated last year
- โ87Updated last year
- some common Huggingface transformers in maximal update parametrization (ยตP)โ82Updated 3 years ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.โ84Updated last month
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.โ70Updated last year
- โ166Updated 2 years ago
- supporting pytorch FSDP for optimizersโ84Updated 8 months ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)โ81Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amountโฆโ53Updated last year
- Universal Neurons in GPT2 Language Modelsโ30Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ241Updated 2 months ago
- PyTorch library for Active Fine-Tuningโ89Updated 6 months ago
- Sparse Autoencoder Training Libraryโ54Updated 3 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ131Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS โฆโ61Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffingโ58Updated 9 months ago
- โ139Updated last week
- Replicating O1 inference-time scaling lawsโ89Updated 8 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from eโฆโ28Updated last year
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023โ136Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"โ77Updated 9 months ago
- โ184Updated last year