Quantization made by Richard Erkhov.

Github

Discord

Request more models

05_rendoo_luman0005_57 - GGUF

• Model creator: https://huggingface.co/rendoo/
• Original model: https://huggingface.co/rendoo/05_rendoo_luman0005_57/

Name	Quant method	Size
05_rendoo_luman0005_57.Q2_K.gguf	Q2_K	2.96GB
05_rendoo_luman0005_57.IQ3_XS.gguf	IQ3_XS	3.28GB
05_rendoo_luman0005_57.IQ3_S.gguf	IQ3_S	3.43GB
05_rendoo_luman0005_57.Q3_K_S.gguf	Q3_K_S	3.41GB
05_rendoo_luman0005_57.IQ3_M.gguf	IQ3_M	3.52GB
05_rendoo_luman0005_57.Q3_K.gguf	Q3_K	3.74GB
05_rendoo_luman0005_57.Q3_K_M.gguf	Q3_K_M	3.74GB
05_rendoo_luman0005_57.Q3_K_L.gguf	Q3_K_L	4.03GB
05_rendoo_luman0005_57.IQ4_XS.gguf	IQ4_XS	4.18GB
05_rendoo_luman0005_57.Q4_0.gguf	Q4_0	4.34GB
05_rendoo_luman0005_57.IQ4_NL.gguf	IQ4_NL	4.38GB
05_rendoo_luman0005_57.Q4_K_S.gguf	Q4_K_S	4.37GB
05_rendoo_luman0005_57.Q4_K.gguf	Q4_K	4.58GB
05_rendoo_luman0005_57.Q4_K_M.gguf	Q4_K_M	4.58GB
05_rendoo_luman0005_57.Q4_1.gguf	Q4_1	4.78GB
05_rendoo_luman0005_57.Q5_0.gguf	Q5_0	5.21GB
05_rendoo_luman0005_57.Q5_K_S.gguf	Q5_K_S	5.21GB
05_rendoo_luman0005_57.Q5_K.gguf	Q5_K	5.34GB
05_rendoo_luman0005_57.Q5_K_M.gguf	Q5_K_M	5.34GB
05_rendoo_luman0005_57.Q5_1.gguf	Q5_1	5.65GB
05_rendoo_luman0005_57.Q6_K.gguf	Q6_K	6.14GB
05_rendoo_luman0005_57.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: [] library_name: transformers tags:

• mergekit
• merge

---

model

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

Merge Details

Merge Method

This model was merged using the linear merge method using /root/model2 as a base.

Models Merged

The following models were included in the merge:

• /root/model1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /root/model2
    parameters:
      weight: 0.9475
  - model: /root/model1
    parameters:
      weight: 0.0525
base_model: /root/model2      
merge_method: linear
dtype: bfloat16