foundation-model-stack / fms-model-optimizerLinks
FMS Model Optimizer is a framework for developing reduced precision neural network models.
☆20Updated last week
Alternatives and similar repositories for fms-model-optimizer
Users that are interested in fms-model-optimizer are comparing it to the libraries listed below
Sorting:
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated 3 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- ☆51Updated 7 months ago
- a pipeline for using api calls to agnostically convert unstructured data into structured training data☆30Updated 9 months ago
- entropix style sampling + GUI☆26Updated 7 months ago
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- ☆47Updated 4 months ago
- Minimum Description Length probing for neural network representations☆18Updated 4 months ago
- Latent Large Language Models☆18Updated 10 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Modified Beam Search with periodical restart☆12Updated 9 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- A library for simplifying fine tuning with multi gpu setups in the Huggingface ecosystem.☆16Updated 8 months ago
- ☆35Updated last year
- ☆22Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆58Updated last month
- Efficient encoder-decoder architecture for small language models (≤1B parameters) with cross-architecture knowledge distillation and visi…☆27Updated 4 months ago
- GoldFinch and other hybrid transformer components☆45Updated 11 months ago
- Lego for GRPO☆28Updated 3 weeks ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- implementation of https://arxiv.org/pdf/2312.09299☆21Updated 11 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated 7 months ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- Analysis on the cost of encoder based models☆11Updated 4 months ago
- QLoRA for Masked Language Modeling☆22Updated last year
- ☆22Updated last year
- QLoRA with Enhanced Multi GPU Support☆37Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated 2 months ago