IBM / ModuleFormerLinks
ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward experts. We released a collection of ModuleFormer-based Language Models (MoLM) ranging in scale from 4 billion to 8 billion parameters.
☆220Updated last year
Alternatives and similar repositories for ModuleFormer
Users that are interested in ModuleFormer are comparing it to the libraries listed below
Sorting:
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆202Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆188Updated 9 months ago
- ☆95Updated last year
- Code repository for the c-BTM paper☆106Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated 11 months ago
- Experiments on speculative sampling with Llama models☆126Updated last year
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆196Updated last year
- Evaluating LLMs with CommonGen-Lite☆90Updated last year
- This is the repo for the paper Shepherd -- A Critic for Language Model Generation☆218Updated last year
- Just a bunch of benchmark logs for different LLMs☆118Updated 10 months ago
- Simple next-token-prediction for RLHF☆226Updated last year
- Scripts for generating synthetic finetuning data for reducing sycophancy.☆111Updated last year
- ☆133Updated last year
- Self-Alignment with Principle-Following Reward Models☆161Updated 3 weeks ago
- DSIR large-scale data selection framework for language model training☆249Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆275Updated last year
- ☆149Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆123Updated last year
- ☆412Updated last year
- ☆121Updated 11 months ago
- LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)☆135Updated 6 months ago
- ☆258Updated last year
- ☆131Updated 6 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆257Updated 10 months ago
- ☆120Updated 8 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆201Updated 3 weeks ago
- Pre-training code for Amber 7B LLM☆166Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆143Updated 8 months ago
- ☆197Updated 5 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year