Edit model card

Noromaid-13b-v0.3 2bit QUIP#

Description

QUIP quant of NeverSleep/Noromaid-13b-v0.3

I wanted to try quanting in QUIP, it took about 20 hours but it works, its coherent and really tiny

Other quants:

EXL2: 8bpw, 6bpw, 5bpw, 4bpw

Prompt Format

Silly Tavern Preset

Instruct template

Context template

Alpaca:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Input:
{input}

### Response:

Contact

Kooten on discord

Downloads last month
5
Safetensors
Model size
728M params
Tensor type
I64
·
FP16
·
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.

Collection including Kooten/Noromaid-13b-v0.3-QUIP-2bit