CoolFace
Modelpublic

Flexan/Novaciano-NPC-1B-PERVERTIDO-GGUF

sourceHugging Faceupdated 7mo agoView on Hugging Face
1likes227downloads
Model Card

GGUF Files for NPC-1B-PERVERTIDO

These are the GGUF files for Novaciano/NPC-1B-PERVERTIDO.

Downloads

GGUF LinkQuantizationDescription
DownloadQ2_KLowest quality
DownloadQ3KS
DownloadIQ3_SInteger quant, preferable over Q3KS
DownloadIQ3_MInteger quant
DownloadQ3KM
DownloadQ3KL
DownloadIQ4_XSInteger quant
DownloadQ4KSFast with good performance
DownloadQ4KMRecommended: Perfect mix of speed and performance
DownloadQ5KS
DownloadQ5KM
DownloadQ6_KVery good quality
DownloadQ8_0Best quality
Downloadf16Full precision, don't bother; use a quant

Note from Flexan

I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet, usually for models I deem interesting and wish to try out.

If there are some quants missing that you'd like me to add, you may request one in the community tab. If you want to request a public model to be converted, you can also request that in the community tab. If you have questions regarding this model, please refer to the original model repo.

You can find more info about me and what I do here.

merged_npc

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: slerp
dtype: float16
out_dtype: float16

base_model: Novaciano/Toxic.NPC-1B

models:
  - model: Novaciano/Toxic.NPC-1B
    parameters:
      weight: 0.55
  - model: hereticness/Heretic-Gemma-3-1B-Instruct-TrashMix-v1.1
    parameters:
      weight: 0.30


parameters:
  t: 0.40
  normalize: false
  rescale: true
  memory_efficient: true
  low_cpu_mem_usage: true