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: 0.25
  • Experts pruned: 8
  • Experts retained: 24
  • Actual ratio: 25.00%
  • Local output dir: layerwise_reap-renorm_true-seed_42-0.25

Provenance

  • Created with Codex using GPT-5.5.
  • Generated for the REAP pruning experiment log and multilingual evaluation.
Downloads last month
17
Safetensors
Model size
1B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sasa2000/granite-3.1-1b-a400m-instruct-reap-pruned-025