sandwichdoge/Nous-Capybara-limarpv3-34B-4.65bpw-hb6-exl2

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

Using erotiquantxl.parquet as calibration dataset.

4.65bpw - Can run 21k context in ~23.3GB VRAM with 8bit-cache option.

Prompt format - extended alpaca with length modifier:

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{instruction}

### Input:
{input}

### Response: (length = long)