metadata
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
Exllamav2 4.65bpw quantization of CausalLM-RP-34B from NeverSleep, quantized with default calibration dataset.
Fits in 24GB VRAM with 32k+ context. Make sure to enable 4-bit cache option or you'll run into OOM errors.
Original Card
Description
This repo contains fp16 files of CausalLM-RP-34B, a finetuned model of the CausalLM-34B Beta on multiple RP datasets.
Model used
Prompt template ChatML
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
{output}<|im_end|>