You can deploy this model and start earning money today!

RichardErkhov/
kromcomp_-_L3-Ceto-Epith-Humanity-v0.1-8B-gguf

Name: kromcomp_-_L3-Ceto-Epith-Humanity-v0.1-8B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3-Ceto-Epith-Humanity-v0.1-8B - GGUF

Model creator: https://huggingface.co/kromcomp/
Original model: https://huggingface.co/kromcomp/L3-Ceto-Epith-Humanity-v0.1-8B/

Name	Quant method	Size
L3-Ceto-Epith-Humanity-v0.1-8B.Q2_K.gguf	Q2_K	2.96GB
L3-Ceto-Epith-Humanity-v0.1-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
L3-Ceto-Epith-Humanity-v0.1-8B.IQ3_S.gguf	IQ3_S	3.43GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
L3-Ceto-Epith-Humanity-v0.1-8B.IQ3_M.gguf	IQ3_M	3.52GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q3_K.gguf	Q3_K	3.74GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
L3-Ceto-Epith-Humanity-v0.1-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q4_0.gguf	Q4_0	4.34GB
L3-Ceto-Epith-Humanity-v0.1-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q4_K.gguf	Q4_K	4.58GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q4_1.gguf	Q4_1	4.78GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q5_0.gguf	Q5_0	5.21GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q5_K.gguf	Q5_K	5.34GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q5_1.gguf	Q5_1	5.65GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q6_K.gguf	Q6_K	6.14GB
L3-Ceto-Epith-Humanity-v0.1-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: [] library_name: transformers tags:

mergekit
merge

humanity

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

Merge Details

Merge Method

This model was merged using the linear DARE merge method using merge/humanity.b as a base.

Models Merged

The following models were included in the merge:

merge/humanity.a

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: merge/humanity.b
dtype: float32
merge_method: dare_linear
out_dtype: bfloat16
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 32]
    model: merge/humanity.b
    parameters:
      weight: 0.5
  - layer_range: [0, 32]
    model: merge/humanity.a
    parameters:
      weight: 0.6
tokenizer_source: base

RichardErkhov/kromcomp_-_L3-Ceto-Epith-Humanity-v0.1-8B-gguf