Quantization made by Richard Erkhov.

Bio-Saul-Dolphin-Beagle-Breadcrumbs - GGUF

Model creator: https://huggingface.co/varox34/
Original model: https://huggingface.co/varox34/Bio-Saul-Dolphin-Beagle-Breadcrumbs/

Name	Quant method	Size
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q2_K.gguf	Q2_K	2.53GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ3_XS.gguf	IQ3_XS	2.81GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ3_S.gguf	IQ3_S	2.96GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K_S.gguf	Q3_K_S	2.95GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ3_M.gguf	IQ3_M	3.06GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K.gguf	Q3_K	3.28GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K_M.gguf	Q3_K_M	3.28GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K_L.gguf	Q3_K_L	3.56GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ4_XS.gguf	IQ4_XS	3.67GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_0.gguf	Q4_0	3.83GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ4_NL.gguf	IQ4_NL	3.87GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_K_S.gguf	Q4_K_S	3.86GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_K.gguf	Q4_K	4.07GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_K_M.gguf	Q4_K_M	4.07GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_1.gguf	Q4_1	4.24GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_0.gguf	Q5_0	4.65GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_K_S.gguf	Q5_K_S	4.65GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_K.gguf	Q5_K	4.78GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_K_M.gguf	Q5_K_M	4.78GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_1.gguf	Q5_1	5.07GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q6_K.gguf	Q6_K	5.53GB
Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model: - cognitivecomputations/dolphin-2.6-mistral-7b - Equall/Saul-Instruct-v1 - BioMistral/BioMistral-7B-SLERP - mlabonne/NeuralBeagle14-7B library_name: transformers tags: - mergekit - merge license: mit

med-law-dolphin-beagle-merge

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

Merge Details

Merge Method

This model was merged using the breadcrumbs merge method using mlabonne/NeuralBeagle14-7B 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: Equall/Saul-Instruct-v1
    parameters:
      weight: 1.0
  - model: BioMistral/BioMistral-7B-SLERP
    parameters:
      weight: 1.0
  - model: cognitivecomputations/dolphin-2.6-mistral-7b
    parameters:
      weight: 0.5
merge_method: breadcrumbs
base_model: mlabonne/NeuralBeagle14-7B

parameters:
    density: 0.9
    gamma: 0.01    
dtype: float16