Hugging Face's logo

nsfwthrowitaway69
/
Venus-120b-v1.2

Text Generation
Transformers
Safetensors
English
llama
Not-For-All-Audiences
text-generation-inference
Inference Endpoints
Model card Files Community
9
Venus-120b-v1.2 / README.md
librarian-bot's picture
librarian-bot
Librarian Bot: Add merge tag to model
7861dbe verified
preview code
|
raw
history blame
1.08 kB
metadata
language:
  - en
license: llama2
tags:
  - not-for-all-audiences
  - merge

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.