You can deploy this model and start earning money today!

RichardErkhov/
mergekit-community_-_config_smart_ablit-gguf

Name: mergekit-community_-_config_smart_ablit-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

config_smart_ablit - GGUF

Model creator: https://huggingface.co/mergekit-community/
Original model: https://huggingface.co/mergekit-community/config_smart_ablit/

Name	Quant method	Size
config_smart_ablit.Q2_K.gguf	Q2_K	2.96GB
config_smart_ablit.IQ3_XS.gguf	IQ3_XS	3.28GB
config_smart_ablit.IQ3_S.gguf	IQ3_S	3.43GB
config_smart_ablit.Q3_K_S.gguf	Q3_K_S	3.41GB
config_smart_ablit.IQ3_M.gguf	IQ3_M	3.52GB
config_smart_ablit.Q3_K.gguf	Q3_K	3.74GB
config_smart_ablit.Q3_K_M.gguf	Q3_K_M	3.74GB
config_smart_ablit.Q3_K_L.gguf	Q3_K_L	4.03GB
config_smart_ablit.IQ4_XS.gguf	IQ4_XS	4.18GB
config_smart_ablit.Q4_0.gguf	Q4_0	4.34GB
config_smart_ablit.IQ4_NL.gguf	IQ4_NL	4.38GB
config_smart_ablit.Q4_K_S.gguf	Q4_K_S	4.37GB
config_smart_ablit.Q4_K.gguf	Q4_K	4.58GB
config_smart_ablit.Q4_K_M.gguf	Q4_K_M	4.58GB
config_smart_ablit.Q4_1.gguf	Q4_1	4.78GB
config_smart_ablit.Q5_0.gguf	Q5_0	5.21GB
config_smart_ablit.Q5_K_S.gguf	Q5_K_S	5.21GB
config_smart_ablit.Q5_K.gguf	Q5_K	5.34GB
config_smart_ablit.Q5_K_M.gguf	Q5_K_M	5.34GB
config_smart_ablit.Q5_1.gguf	Q5_1	5.65GB
config_smart_ablit.Q6_K.gguf	Q6_K	6.14GB
config_smart_ablit.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
Solshine/reflection-llama-3.1-8B
grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
huihui-ai/deepthought-8b-abliterated
vicgalle/Configurable-Hermes-3-Llama-3.1-8B 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 Model Stock merge method using vicgalle/Configurable-Hermes-3-Llama-3.1-8B 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

models:   
  - model: huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
  - model: Solshine/reflection-llama-3.1-8B
  - model: huihui-ai/deepthought-8b-abliterated
  - model: grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
merge_method: model_stock
base_model: vicgalle/Configurable-Hermes-3-Llama-3.1-8B
dtype: bfloat16

RichardErkhov/mergekit-community_-_config_smart_ablit-gguf