You can deploy this model and start earning money today!

RichardErkhov/
Hjgugugjhuhjggg_-_mergekit-ties-dwvvsov-gguf

Name: Hjgugugjhuhjggg_-_mergekit-ties-dwvvsov-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-ties-dwvvsov - GGUF

Model creator: https://huggingface.co/Hjgugugjhuhjggg/
Original model: https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-dwvvsov/

Name	Quant method	Size
mergekit-ties-dwvvsov.Q2_K.gguf	Q2_K	1.39GB
mergekit-ties-dwvvsov.IQ3_XS.gguf	IQ3_XS	1.53GB
mergekit-ties-dwvvsov.IQ3_S.gguf	IQ3_S	1.59GB
mergekit-ties-dwvvsov.Q3_K_S.gguf	Q3_K_S	1.59GB
mergekit-ties-dwvvsov.IQ3_M.gguf	IQ3_M	1.65GB
mergekit-ties-dwvvsov.Q3_K.gguf	Q3_K	1.73GB
mergekit-ties-dwvvsov.Q3_K_M.gguf	Q3_K_M	1.73GB
mergekit-ties-dwvvsov.Q3_K_L.gguf	Q3_K_L	1.85GB
mergekit-ties-dwvvsov.IQ4_XS.gguf	IQ4_XS	1.91GB
mergekit-ties-dwvvsov.Q4_0.gguf	Q4_0	1.99GB
mergekit-ties-dwvvsov.IQ4_NL.gguf	IQ4_NL	2.0GB
mergekit-ties-dwvvsov.Q4_K_S.gguf	Q4_K_S	2.0GB
mergekit-ties-dwvvsov.Q4_K.gguf	Q4_K	2.09GB
mergekit-ties-dwvvsov.Q4_K_M.gguf	Q4_K_M	2.09GB
mergekit-ties-dwvvsov.Q4_1.gguf	Q4_1	2.18GB
mergekit-ties-dwvvsov.Q5_0.gguf	Q5_0	2.37GB
mergekit-ties-dwvvsov.Q5_K_S.gguf	Q5_K_S	2.37GB
mergekit-ties-dwvvsov.Q5_K.gguf	Q5_K	2.41GB
mergekit-ties-dwvvsov.Q5_K_M.gguf	Q5_K_M	2.41GB
mergekit-ties-dwvvsov.Q5_1.gguf	Q5_1	2.55GB
mergekit-ties-dwvvsov.Q6_K.gguf	Q6_K	2.76GB
mergekit-ties-dwvvsov.Q8_0.gguf	Q8_0	3.58GB

Original model description:

base_model:

chuanli11/Llama-3.2-3B-Instruct-uncensored
meta-llama/Llama-3.2-3B-Instruct
huihui-ai/Llama-3.2-3B-Instruct-abliterated
meta-llama/Llama-3.2-3B
bunnycore/Llama-3.2-3B-ProdigyPlusPlus library_name: transformers tags:
mergekit
merge

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model:
  model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
merge_method: ties
merge_method_sequence:
- dare_ties
- slerp
- ties
models:
- model: meta-llama/Llama-3.2-3B-Instruct
- model: meta-llama/Llama-3.2-3B
- model: chuanli11/Llama-3.2-3B-Instruct-uncensored
- model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
- model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
parameters:
  density: 0.5
  int8_mask: true
  layer_range:
  - 0
  - 28
  normalize: false
  weight: 0.5
tokenizer_source: union

RichardErkhov/Hjgugugjhuhjggg_-_mergekit-ties-dwvvsov-gguf