CoolFace
Modelpublic

sasa2000/granite-3.1-1b-a400m-instruct-reap-pruned-020

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes9downloads
Model Card

Granite 3.1 1B A400M Instruct REAP Pruned Checkpoint

This repository contains a REAP layerwise-pruned checkpoint of ibm-granite/granite-3.1-1b-a400m-instruct.

Base Model

  • —Model: ibm-granite/granite-3.1-1b-a400m-instruct
  • —Architecture: GraniteMoeForCausalLM
  • —num_local_experts=32
  • —num_experts_per_tok=8

Pruning Setup

  • —Dataset: theblackcat102/evol-codealpaca-v1
  • —model_max_length=2048
  • —batches_per_category=128
  • —batch_size=1
  • —batch_group_size=8
  • —renormalize_router_weights=true
  • —truncate=false

Checkpoint

  • —Requested ratio: 0.20
  • —Experts pruned: 6
  • —Experts retained: 26
  • —Actual ratio: 18.75%
  • —Local output dir: layerwise_reap-renorm_true-seed_42-0.19

Provenance

  • —Created with Codex using GPT-5.5.
  • —Generated for the REAP pruning experiment log and multilingual evaluation.