You can deploy this model and start earning money today!

RichardErkhov/
TeeZee_-_BigMaid-20B-v2.0-gguf

Name: TeeZee_-_BigMaid-20B-v2.0-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

BigMaid-20B-v2.0 - GGUF

Model creator: https://huggingface.co/TeeZee/
Original model: https://huggingface.co/TeeZee/BigMaid-20B-v2.0/

Name	Quant method	Size
BigMaid-20B-v2.0.Q2_K.gguf	Q2_K	6.91GB
BigMaid-20B-v2.0.Q3_K_S.gguf	Q3_K_S	8.06GB
BigMaid-20B-v2.0.Q3_K.gguf	Q3_K	9.04GB
BigMaid-20B-v2.0.Q3_K_M.gguf	Q3_K_M	9.04GB
BigMaid-20B-v2.0.Q3_K_L.gguf	Q3_K_L	9.9GB
BigMaid-20B-v2.0.IQ4_XS.gguf	IQ4_XS	10.01GB
BigMaid-20B-v2.0.Q4_0.gguf	Q4_0	10.52GB
BigMaid-20B-v2.0.IQ4_NL.gguf	IQ4_NL	10.57GB
BigMaid-20B-v2.0.Q4_K_S.gguf	Q4_K_S	10.59GB
BigMaid-20B-v2.0.Q4_K.gguf	Q4_K	11.22GB
BigMaid-20B-v2.0.Q4_K_M.gguf	Q4_K_M	11.22GB
BigMaid-20B-v2.0.Q4_1.gguf	Q4_1	11.67GB
BigMaid-20B-v2.0.Q5_0.gguf	Q5_0	12.83GB
BigMaid-20B-v2.0.Q5_K_S.gguf	Q5_K_S	12.83GB
BigMaid-20B-v2.0.Q5_K.gguf	Q5_K	13.18GB
BigMaid-20B-v2.0.Q5_K_M.gguf	Q5_K_M	13.18GB
BigMaid-20B-v2.0.Q5_1.gguf	Q5_1	13.98GB
BigMaid-20B-v2.0.Q6_K.gguf	Q6_K	15.28GB
BigMaid-20B-v2.0.Q8_0.gguf	Q8_0	19.79GB

Original model description:

language:

en license: apache-2.0 library_name: transformers tags:
roleplay
text-generation-inference
mergekit
merge
not-for-all-audiences

BigMaid-20B-v2.0

This is a merge of pre-trained language models created using mergekit. FP32 version

Tests

model retains qualities of BigMaid-20B-v1.0 and it's also more creative and coherent.

Merge Details

Merge Method

This model was merged using the passthrough merge method.
Merge parameters were inspired by work of DavidAU and jukofyork
thread
thread

Models Merged

The following models were included in the merge:

KatyTheCutie_EstopianMaid-13B

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
    - model: "./KatyTheCutie_EstopianMaid-13B"
      layer_range: [0, 16]
      parameters:
      scale:
        - filter: q_proj
          value: 0.7071067812
        - filter: k_proj
          value: 0.7071067812
        - value: 1
  - sources:
    - model: "./KatyTheCutie_EstopianMaid-13B"
      layer_range: [8, 24]
      parameters:
      scale:
        - filter: q_proj
          value: 0.7071067812
        - filter: k_proj
          value: 0.7071067812
        - value: 1
  - sources:
    - model: "./KatyTheCutie_EstopianMaid-13B"
      layer_range: [17, 32]
      parameters:
      scale:
        - filter: q_proj
          value: 0.7071067812
        - filter: k_proj
          value: 0.7071067812
        - value: 1
  - sources:
    - model: "./KatyTheCutie_EstopianMaid-13B"
      layer_range: [25, 40]
      parameters:
      scale:
        - filter: q_proj
          value: 0.7071067812
        - filter: k_proj
          value: 0.7071067812
        - value: 1
merge_method: passthrough
dtype: float32

All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:

RichardErkhov/TeeZee_-_BigMaid-20B-v2.0-gguf