Edit model card

This is a merge of Xwin and WinterGoddess, both extended to 32k using the method discussed here.

Smarter than Goliath-32k, but has some quirks.

A bit damaged compared to original WinterGoliath.

Prompt format

Vicuna or Alpaca.

Benchmarks

NeoEvalPlusN_benchmark

My meme benchmark.

Test name WinterGoliath-32k WinterGoliath
B 3 3
C 2 2
D 1 2
S 3.75 5.5
P 3.75 6
Total 13.5 18.5
Downloads last month
6
Safetensors
Model size
124B params
Tensor type
FP16
·
Inference API
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-32k

Quantizations
2 models

Collection including ChuckMcSneed/WinterGoliath-123b-32k