You can deploy this model and start earning money today!

RichardErkhov/
legacymodel_-_Badudu-8B-instruct-v1-TIES-Hrududu-gguf

Name: legacymodel_-_Badudu-8B-instruct-v1-TIES-Hrududu-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Badudu-8B-instruct-v1-TIES-Hrududu - GGUF

Model creator: https://huggingface.co/legacymodel/
Original model: https://huggingface.co/legacymodel/Badudu-8B-instruct-v1-TIES-Hrududu/

Name	Quant method	Size
Badudu-8B-instruct-v1-TIES-Hrududu.Q2_K.gguf	Q2_K	2.96GB
Badudu-8B-instruct-v1-TIES-Hrududu.IQ3_XS.gguf	IQ3_XS	3.28GB
Badudu-8B-instruct-v1-TIES-Hrududu.IQ3_S.gguf	IQ3_S	3.43GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q3_K_S.gguf	Q3_K_S	3.41GB
Badudu-8B-instruct-v1-TIES-Hrududu.IQ3_M.gguf	IQ3_M	3.52GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q3_K.gguf	Q3_K	3.74GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q3_K_M.gguf	Q3_K_M	3.74GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q3_K_L.gguf	Q3_K_L	4.03GB
Badudu-8B-instruct-v1-TIES-Hrududu.IQ4_XS.gguf	IQ4_XS	4.18GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q4_0.gguf	Q4_0	4.34GB
Badudu-8B-instruct-v1-TIES-Hrududu.IQ4_NL.gguf	IQ4_NL	4.38GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q4_K_S.gguf	Q4_K_S	4.37GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q4_K.gguf	Q4_K	4.58GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q4_K_M.gguf	Q4_K_M	4.58GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q4_1.gguf	Q4_1	4.78GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q5_0.gguf	Q5_0	5.21GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q5_K_S.gguf	Q5_K_S	5.21GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q5_K.gguf	Q5_K	5.34GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q5_K_M.gguf	Q5_K_M	5.34GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q5_1.gguf	Q5_1	5.65GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q6_K.gguf	Q6_K	6.14GB
Badudu-8B-instruct-v1-TIES-Hrududu.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc
gmonsoon/Badudu-8B-instruct-v1 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 djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc as a base.

Models Merged

The following models were included in the merge:

gmonsoon/Badudu-8B-instruct-v1

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc
    #no parameters necessary for base model
  - model: gmonsoon/Badudu-8B-instruct-v1
    parameters:
      density: 1
      weight: 1
  - model: djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc
    parameters:
      density: 1
      weight: 1
tokenizer_source: gmonsoon/Badudu-8B-instruct-v1
merge_method: ties
base_model: djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

RichardErkhov/legacymodel_-_Badudu-8B-instruct-v1-TIES-Hrududu-gguf