epfml / llm-baselinesLinks
nanoGPT-like codebase for LLM training
โ109Updated 5 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:
- A MAD laboratory to improve AI architecture designs ๐งชโ131Updated 10 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ168Updated 4 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"โ84Updated 11 months ago
- Understand and test language model architectures on synthetic tasks.โ233Updated last month
- โ53Updated last year
- some common Huggingface transformers in maximal update parametrization (ยตP)โ86Updated 3 years ago
- โ83Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"โ241Updated 4 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.โ69Updated last year
- PyTorch library for Active Fine-Tuningโ93Updated last month
- Language models scale reliably with over-training and on downstream tasksโ100Updated last year
- โ58Updated last year
- Code for studying the super weight in LLMโ120Updated 10 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ193Updated last year
- โ91Updated 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 amountโฆโ52Updated 2 years ago
- Simple and efficient pytorch-native transformer training and inference (batched)โ78Updated last year
- supporting pytorch FSDP for optimizersโ83Updated 10 months ago
- โ86Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.โ92Updated 3 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ132Updated last year
- โ41Updated this week
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)โ80Updated 2 years ago
- โ166Updated 2 years ago
- โ38Updated last year
- โ142Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffingโ59Updated 11 months ago
- Universal Neurons in GPT2 Language Modelsโ30Updated last year
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023โ136Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersโ130Updated 10 months ago