You can deploy this model and start earning money today!

RichardErkhov/
ssktora_-_biomed_e57b_notevo_merge_slerp-gguf

Name: ssktora_-_biomed_e57b_notevo_merge_slerp-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

biomed_e57b_notevo_merge_slerp - GGUF

Model creator: https://huggingface.co/ssktora/
Original model: https://huggingface.co/ssktora/biomed_e57b_notevo_merge_slerp/

Name	Quant method	Size
biomed_e57b_notevo_merge_slerp.Q2_K.gguf	Q2_K	2.53GB
biomed_e57b_notevo_merge_slerp.IQ3_XS.gguf	IQ3_XS	2.81GB
biomed_e57b_notevo_merge_slerp.IQ3_S.gguf	IQ3_S	2.96GB
biomed_e57b_notevo_merge_slerp.Q3_K_S.gguf	Q3_K_S	2.95GB
biomed_e57b_notevo_merge_slerp.IQ3_M.gguf	IQ3_M	3.06GB
biomed_e57b_notevo_merge_slerp.Q3_K.gguf	Q3_K	3.28GB
biomed_e57b_notevo_merge_slerp.Q3_K_M.gguf	Q3_K_M	3.28GB
biomed_e57b_notevo_merge_slerp.Q3_K_L.gguf	Q3_K_L	3.56GB
biomed_e57b_notevo_merge_slerp.IQ4_XS.gguf	IQ4_XS	3.67GB
biomed_e57b_notevo_merge_slerp.Q4_0.gguf	Q4_0	3.83GB
biomed_e57b_notevo_merge_slerp.IQ4_NL.gguf	IQ4_NL	3.87GB
biomed_e57b_notevo_merge_slerp.Q4_K_S.gguf	Q4_K_S	3.86GB
biomed_e57b_notevo_merge_slerp.Q4_K.gguf	Q4_K	4.07GB
biomed_e57b_notevo_merge_slerp.Q4_K_M.gguf	Q4_K_M	4.07GB
biomed_e57b_notevo_merge_slerp.Q4_1.gguf	Q4_1	4.24GB
biomed_e57b_notevo_merge_slerp.Q5_0.gguf	Q5_0	4.65GB
biomed_e57b_notevo_merge_slerp.Q5_K_S.gguf	Q5_K_S	4.65GB
biomed_e57b_notevo_merge_slerp.Q5_K.gguf	Q5_K	4.78GB
biomed_e57b_notevo_merge_slerp.Q5_K_M.gguf	Q5_K_M	4.78GB
biomed_e57b_notevo_merge_slerp.Q5_1.gguf	Q5_1	5.07GB
biomed_e57b_notevo_merge_slerp.Q6_K.gguf	Q6_K	5.53GB
biomed_e57b_notevo_merge_slerp.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model: [] library_name: transformers tags:

mergekit
merge

notevo_merge_biomistral_e57b_slerp

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

./e5-mistral-7b-instruct_with_lm_head
./local_BioMistral-7B

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: ./e5-mistral-7b-instruct_with_lm_head
        layer_range: [0, 32]
      - model: ./local_BioMistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: ./e5-mistral-7b-instruct_with_lm_head
parameters:
  t:
    - value: [0.5, 0.1]

merge_method: slerp
dtype: float16

RichardErkhov/ssktora_-_biomed_e57b_notevo_merge_slerp-gguf