|
--- |
|
license: other |
|
--- |
|
[WizardLM-33B-V1.0-Uncensored](https://huggingface.co/ehartford/WizardLM-33B-V1.0-Uncensored) merged with kaiokendev's [33b SuperHOT 8k LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test), quantized at 4 bit. |
|
|
|
It was created with GPTQ-for-LLaMA with group size 32 and act order true as parameters, to get the maximum perplexity vs FP16 model. |
|
|
|
I HIGHLY suggest to use exllama, to evade some VRAM issues. |
|
|
|
Use compress_pos_emb = 4 for any context up to 8192 context. |
|
|
|
If you have 2x24 GB VRAM GPUs cards, to not get Out of Memory errors at 8192 context, use: |
|
|
|
gpu_split: 9,21 |