You can deploy this model and start earning money today!

RichardErkhov/
Nisk36_-_MergeModel10-gguf

Name: Nisk36_-_MergeModel10-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MergeModel10 - GGUF

Model creator: https://huggingface.co/Nisk36/
Original model: https://huggingface.co/Nisk36/MergeModel10/

Name	Quant method	Size
MergeModel10.Q2_K.gguf	Q2_K	2.36GB
MergeModel10.IQ3_XS.gguf	IQ3_XS	2.6GB
MergeModel10.IQ3_S.gguf	IQ3_S	2.75GB
MergeModel10.Q3_K_S.gguf	Q3_K_S	2.75GB
MergeModel10.IQ3_M.gguf	IQ3_M	2.9GB
MergeModel10.Q3_K.gguf	Q3_K	3.07GB
MergeModel10.Q3_K_M.gguf	Q3_K_M	3.07GB
MergeModel10.Q3_K_L.gguf	Q3_K_L	3.35GB
MergeModel10.IQ4_XS.gguf	IQ4_XS	3.4GB
MergeModel10.Q4_0.gguf	Q4_0	3.56GB
MergeModel10.IQ4_NL.gguf	IQ4_NL	3.58GB
MergeModel10.Q4_K_S.gguf	Q4_K_S	3.59GB
MergeModel10.Q4_K.gguf	Q4_K	3.8GB
MergeModel10.Q4_K_M.gguf	Q4_K_M	3.8GB
MergeModel10.Q4_1.gguf	Q4_1	3.95GB
MergeModel10.Q5_0.gguf	Q5_0	4.33GB
MergeModel10.Q5_K_S.gguf	Q5_K_S	4.33GB
MergeModel10.Q5_K.gguf	Q5_K	4.45GB
MergeModel10.Q5_K_M.gguf	Q5_K_M	4.45GB
MergeModel10.Q5_1.gguf	Q5_1	4.72GB
MergeModel10.Q6_K.gguf	Q6_K	5.15GB
MergeModel10.Q8_0.gguf	Q8_0	6.67GB

Original model description:

base_model:

Nisk36/finetuned-lmsys_vicuna-7b-v1.5
Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct library_name: transformers tags:
mergekit
merge

final_model

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

dtype: bfloat16
merge_method: linear
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 4]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.2314007323608976
  - layer_range: [0, 4]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.6555169289144125
- sources:
  - layer_range: [4, 8]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.40114629790472045
  - layer_range: [4, 8]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.3638313057798464
- sources:
  - layer_range: [8, 12]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.6552004806174763
  - layer_range: [8, 12]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.5932631992622696
- sources:
  - layer_range: [12, 16]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.5796797657003963
  - layer_range: [12, 16]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.5509781091865962
- sources:
  - layer_range: [16, 20]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.3670138586048981
  - layer_range: [16, 20]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.4819576330601912
- sources:
  - layer_range: [20, 24]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.8704563123348978
  - layer_range: [20, 24]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.23823012325912632
- sources:
  - layer_range: [24, 28]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.3527054439651195
  - layer_range: [24, 28]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.7886966464065228
- sources:
  - layer_range: [28, 32]
    model: Nisk36/finetuned-lmsys_vicuna-7b-v1.5
    parameters:
      weight: 0.615452246302311
  - layer_range: [28, 32]
    model: Nisk36/FT_elyza_ELYZA-japanese-Llama-2-7b-instruct
    parameters:
      weight: 0.10099107707206684

RichardErkhov/Nisk36_-_MergeModel10-gguf