sasa2000/granite-3.1-1b-a400m-instruct-reap-pruned-010
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
f62aea79318888c5418ef50a2cec244b2434a8b0
granite-3.1-1b-a400m-instru…/README.md
ModelHub XC f62aea7931 初始化项目，由ModelHub XC社区提供模型 
Model: sasa2000/granite-3.1-1b-a400m-instruct-reap-pruned-010
Source: Original Platform
2026-10-04 04:33:18 +08:00

1004 B
Raw Blame History

base_model, pipeline_tag, tags, license
base_model pipeline_tag tags license
ibm-granite/granite-3.1-1b-a400m-instruct text-generation
granite
reap
pruning
multilingual
apache-2.0

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: 0.10
  • Experts pruned: 3
  • Experts retained: 29
  • Actual ratio: 9.38%
  • Local output dir: layerwise_reap-renorm_true-seed_42-0.09

Provenance

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