Quantization made by Richard Erkhov.

model-4-novem2 - GGUF

Model creator: https://huggingface.co/Sakalti/
Original model: https://huggingface.co/Sakalti/model-4-novem2/

Name	Quant method	Size
model-4-novem2.Q2_K.gguf	Q2_K	0.7GB
model-4-novem2.IQ3_XS.gguf	IQ3_XS	0.77GB
model-4-novem2.IQ3_S.gguf	IQ3_S	0.8GB
model-4-novem2.Q3_K_S.gguf	Q3_K_S	0.8GB
model-4-novem2.IQ3_M.gguf	IQ3_M	0.82GB
model-4-novem2.Q3_K.gguf	Q3_K	0.86GB
model-4-novem2.Q3_K_M.gguf	Q3_K_M	0.86GB
model-4-novem2.Q3_K_L.gguf	Q3_K_L	0.91GB
model-4-novem2.IQ4_XS.gguf	IQ4_XS	0.96GB
model-4-novem2.Q4_0.gguf	Q4_0	0.99GB
model-4-novem2.IQ4_NL.gguf	IQ4_NL	1.0GB
model-4-novem2.Q4_K_S.gguf	Q4_K_S	1.0GB
model-4-novem2.Q4_K.gguf	Q4_K	1.04GB
model-4-novem2.Q4_K_M.gguf	Q4_K_M	1.04GB
model-4-novem2.Q4_1.gguf	Q4_1	1.08GB
model-4-novem2.Q5_0.gguf	Q5_0	1.17GB
model-4-novem2.Q5_K_S.gguf	Q5_K_S	1.17GB
model-4-novem2.Q5_K.gguf	Q5_K	1.2GB
model-4-novem2.Q5_K_M.gguf	Q5_K_M	1.2GB
model-4-novem2.Q5_1.gguf	Q5_1	1.26GB
model-4-novem2.Q6_K.gguf	Q6_K	1.36GB
model-4-novem2.Q8_0.gguf	Q8_0	1.76GB

Original model description:

base_model:

sahandrez/rloo-paired-Qwen2.5-1.5B-ultrafeedback-binarized-20241125-125438
Sakalti/model-4 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 Sakalti/model-4 as a base.

Models Merged

The following models were included in the merge:

sahandrez/rloo-paired-Qwen2.5-1.5B-ultrafeedback-binarized-20241125-125438

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: sahandrez/rloo-paired-Qwen2.5-1.5B-ultrafeedback-binarized-20241125-125438
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: Sakalti/model-4
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16