Venus 120b - version 1.2

image/png

Overview

Version 1.2 of the Venus 120b lineup.

Model Details

  • A result of interleaving layers of lizpreciatior/lzlv_70b_fp16_hf with itself.
  • The resulting model has 140 layers and approximately 122 billion parameters.
  • See mergekit-config.yml for details on the merge method used.
  • See the exl2-* branches for exllama2 quantizations. The 4.85 bpw quant should fit in 80GB VRAM, and the 3.0 bpw quant should (just barely) fit in 48GB VRAM with 4k context.
  • Inspired by Goliath-120b

Warning: This model will produce NSFW content!

Results

Better at following instructions than both v1.1 and v1.0, and doesn't seem to suffer from censorship issues. Overall I like this version the most out of all the models I've created.

Downloads last month
1,401
Safetensors
Model size
120B params
Tensor type
FP16
ยท
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 nsfwthrowitaway69/Venus-120b-v1.2

Quantizations
4 models

Spaces using nsfwthrowitaway69/Venus-120b-v1.2 2