bkitano / llama-from-scratch
Llama from scratch, or How to implement a paper without crying
☆547Updated 9 months ago
Alternatives and similar repositories for llama-from-scratch:
Users that are interested in llama-from-scratch are comparing it to the libraries listed below
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆782Updated last week
- What would you do with 1000 H100s...☆1,013Updated last year
- nanoGPT style version of Llama 3.1☆1,329Updated 7 months ago
- ☆1,079Updated 2 weeks ago
- From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)☆674Updated 4 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,473Updated last year
- LLaMA 2 implemented from scratch in PyTorch☆303Updated last year
- Data and tools for generating and inspecting OLMo pre-training data.☆1,144Updated last week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,215Updated last week
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,367Updated 11 months ago
- Minimalistic large language model 3D-parallelism training☆1,675Updated this week
- Best practices & guides on how to write distributed pytorch training code☆367Updated 2 weeks ago
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆255Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆813Updated this week
- LLM Workshop by Sourab Mangrulkar☆366Updated 8 months ago
- Serving multiple LoRA finetuned LLM as one☆1,036Updated 10 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,092Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆928Updated last week
- Building blocks for foundation models.☆460Updated last year
- The repository for the code of the UltraFastBERT paper☆517Updated 11 months ago
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆999Updated 6 months ago
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆849Updated 3 weeks ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆690Updated 11 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100s☆707Updated last year
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆572Updated 8 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆726Updated 2 months ago
- A bibliography and survey of the papers surrounding o1☆1,177Updated 3 months ago
- Best practices for distilling large language models.☆502Updated last year
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,291Updated last week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆594Updated last year