Quantization made by Richard Erkhov.

EinsteinBagel-8B - GGUF

Model creator: https://huggingface.co/TitleOS/
Original model: https://huggingface.co/TitleOS/EinsteinBagel-8B/

Name	Quant method	Size
EinsteinBagel-8B.Q2_K.gguf	Q2_K	2.96GB
EinsteinBagel-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
EinsteinBagel-8B.IQ3_S.gguf	IQ3_S	3.43GB
EinsteinBagel-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
EinsteinBagel-8B.IQ3_M.gguf	IQ3_M	3.52GB
EinsteinBagel-8B.Q3_K.gguf	Q3_K	3.74GB
EinsteinBagel-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
EinsteinBagel-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
EinsteinBagel-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
EinsteinBagel-8B.Q4_0.gguf	Q4_0	4.34GB
EinsteinBagel-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
EinsteinBagel-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
EinsteinBagel-8B.Q4_K.gguf	Q4_K	4.58GB
EinsteinBagel-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
EinsteinBagel-8B.Q4_1.gguf	Q4_1	4.78GB
EinsteinBagel-8B.Q5_0.gguf	Q5_0	5.21GB
EinsteinBagel-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
EinsteinBagel-8B.Q5_K.gguf	Q5_K	5.34GB
EinsteinBagel-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
EinsteinBagel-8B.Q5_1.gguf	Q5_1	5.65GB
EinsteinBagel-8B.Q6_K.gguf	Q6_K	6.14GB
EinsteinBagel-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: - Weyaxi/Einstein-v6.1-Llama3-8B - meta-llama/Meta-Llama-3-8B - jondurbin/bagel-8b-v1.0 library_name: transformers tags: - mergekit - merge license: llama3

EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0)

This is a merge of pre-trained language models created using mergekit. The purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: meta-llama/Meta-Llama-3-8B
  - model: jondurbin/bagel-8b-v1.0
  - model: Weyaxi/Einstein-v6.1-Llama3-8B
merge_method: model_stock
base_model: meta-llama/Meta-Llama-3-8B
dtype: bfloat16