Edit model card

This is a merge of Xwin and WinterGoddess. Made using mergekit.

Smarter than Goliath, but a bit more aligned. Sidegrade rather than upgrade. Sacrifices neutrality and fun for smartness(on an empty context).

Prompt format

Vicuna or Alpaca.

Quants

Thanks, TheBloke!

32k version

HERE

Benchmarks

NeoEvalPlusN_benchmark

My meme benchmark.

Test name Goliath WinterGoliath
B 3 3
C 2 2
D 1 2
S 5 5.5
P 6 6
Total 17 18.5

Kanye Test

WinterGoliath kinda gets the rhyme, Goliath doesn't. Kanye test

Politiscales test

Politiscales for llama

name whacky left/right
alpindale/goliath-120b 1.066739456 1.544969782
ChuckMcSneed/WinterGoliath-123b 0.518277513 2.735962
Xwin-LM/Xwin-LM-70B-V0.1 1.463521162 1.491684328
Sao10K/WinterGoddess-1.4x-70B-L2 0.384151757 4.747980293
Downloads last month
96
Safetensors
Model size
124B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ChuckMcSneed/WinterGoliath-123b

Quantizations
4 models