apoorvkh / academic-pretrainingLinks
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
☆143Updated 2 months ago
Alternatives and similar repositories for academic-pretraining
Users that are interested in academic-pretraining are comparing it to the libraries listed below
Sorting:
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- ☆136Updated 4 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 6 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- ☆81Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆67Updated 11 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆149Updated last month
- Getting crystal-like representations with harmonic loss☆192Updated 4 months ago
- Collection of autoregressive model implementation☆86Updated 3 months ago
- ☆83Updated 11 months ago
- ☆118Updated 7 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆103Updated 5 months ago
- Implementations of attention with the softpick function, naive and FlashAttention-2☆81Updated 3 months ago
- An introduction to LLM Sampling☆79Updated 7 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆49Updated 3 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆94Updated 2 weeks ago
- A MAD laboratory to improve AI architecture designs 🧪☆123Updated 7 months ago
- PyTorch implementation of models from the Zamba2 series.☆184Updated 6 months ago
- ☆56Updated 8 months ago
- Understand and test language model architectures on synthetic tasks.☆221Updated 3 weeks ago
- ☆172Updated 3 months ago
- code for training & evaluating Contextual Document Embedding models☆196Updated 2 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 7 months ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- ☆83Updated last year
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆94Updated last week
- PyTorch library for Active Fine-Tuning☆87Updated 5 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 11 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆103Updated 3 months ago
- WIP☆94Updated 11 months ago