Downloads · 30 days
14
22% of all-time downloads
sasa2000/granite-3.1-3b-a800m-instruct-reap-pruned-015
granite-3.1-3b-a800m-instruct-reap-pruned-015 is a text generation model from sasa2000. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This repository contains a REAP layerwise-pruned checkpoint of ibm-granite/granite-3.1-3b-a800m-instruct.
Downloads · 30 days
14
22% of all-time downloads
All-time downloads
65
Public
Parameters
2.8B
5.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.7 GB · 100%
From the Hugging Face model README
This repository contains a REAP layerwise-pruned checkpoint of
ibm-granite/granite-3.1-3b-a800m-instruct.
ibm-granite/granite-3.1-3b-a800m-instructGraniteMoeForCausalLMnum_local_experts=40num_experts_per_tok=8theblackcat102/evol-codealpaca-v1model_max_length=2048batches_per_category=128batch_size=1batch_group_size=8renormalize_router_weights=truetruncate=false0.1563415.00%layerwise_reap-renorm_true-seed_42-0.15