Venus 103b - version 1.0
Overview
A smaller version of Venus-120b that uses the same base models.
Model Details
- A result of interleaving layers of Sao10K/Euryale-1.3-L2-70B, NousResearch/Nous-Hermes-Llama2-70b, and migtissera/SynthIA-70B-v1.5 using mergekit.
- The resulting model has 120 layers and approximately 103 billion parameters.
- See mergekit-config.yml for details on the merge method used.
- See the
exl2-*branches for exllama2 quantizations. The 5.65 bpw quant should fit in 80GB VRAM, and the 3.35 bpw quant should fit in 48GB VRAM.
Warning: This model will produce NSFW content!
Results
Seems to be a bit more coherent than Venus-120b, likely due to using SynthIA 1.2b instead of SynthIA 1.5.
- Downloads last month
- 18
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.