Model Card for Model ID

My first exl2 quant of my favourite go-to roleplaying model. Can fit into my empty 24GB VRAM with 32k context in 8-bit cache. Might do a 4.25bpw quant later.

Original model: https://huggingface.co./Doctor-Shotgun/Nous-Capybara-limarpv3-34B

Prompt format: https://github.com/tatsu-lab/stanford_alpaca

Downloads last month: 14

Inference Examples

Text Generation

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.

Dataset used to train MarinaraSpaghetti/Doctor-Shotgun_Nous-Capybara-limarpv3-34B-4.2bpw-h6-exl2

Collection including MarinaraSpaghetti/Doctor-Shotgun_Nous-Capybara-limarpv3-34B-4.2bpw-h6-exl2

EXL2

Collection

EXL2 is the best format. • 4 items • Updated Jul 30