|
Download README.md from flashstep/anlp-assignment2-part1: direct link, hf CLI and curl.
- Browser
- Download file 524 Bytes
-
https://huggingface.co/flashstep/anlp-assignment2-part1/resolve/main/README.md
- Command line
-
hf download hf://flashstep/anlp-assignment2-part1/README.md
-
curl -L -o README.md https://huggingface.co/flashstep/anlp-assignment2-part1/resolve/main/README.md
524 Bytes
ANLP Assignment 2 — Part 1
This repository contains the trained model checkpoints for Part 1 of ANLP Assignment 2.
Model Variants
model_variant_1.pt— Dense 2-layer MLPmodel_variant_2.pt— MoE, 4 experts, Top-1 routingmodel_variant_3.pt— MoE, 4 experts, Top-2 routingmodel_variant_4.pt— Shared + Routed MoEmodel_variant_5.pt— Matched Active-Parameter MoE
The checkpoints are provided in PyTorch .pt format.
See the accompanying report for experimental details and results.