Property	Value
Original Model	upstage/Solar-Open-100B
Original Parameters	43.71B
Pruned Parameters	7.21B
Compression Ratio	0.1650 (6.1x smaller)
Strategy	Layer + FFN (Recommended)
Importance Metric	magnitude
Layers Removed	28
FFN Reduction	0.00%

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("llaa33219/Solar-Open-100B-pruned-5pct")
tokenizer = AutoTokenizer.from_pretrained("llaa33219/Solar-Open-100B-pruned-5pct")

Notes

This model was created using structured pruning techniques including:

Layer pruning (removing entire transformer layers)
FFN dimension pruning (reducing intermediate layer sizes)

The pruning was based on magnitude importance scoring to preserve the most important weights.

llaa33219/Solar-Open-100B-to-7B-test

Solar-Open-100B-pruned-5pct

Pruning Details

Usage

Notes

llaa33219/
Solar-Open-100B-to-7B-test