You can deploy this model and start earning money today!

RichardErkhov/
grimjim_-_Mistral-Starling-merge-trial3-7B-gguf

Name: grimjim_-_Mistral-Starling-merge-trial3-7B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-Starling-merge-trial3-7B - GGUF

Model creator: https://huggingface.co/grimjim/
Original model: https://huggingface.co/grimjim/Mistral-Starling-merge-trial3-7B/

Name	Quant method	Size
Mistral-Starling-merge-trial3-7B.Q2_K.gguf	Q2_K	2.53GB
Mistral-Starling-merge-trial3-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-Starling-merge-trial3-7B.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-Starling-merge-trial3-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-Starling-merge-trial3-7B.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-Starling-merge-trial3-7B.Q3_K.gguf	Q3_K	3.28GB
Mistral-Starling-merge-trial3-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-Starling-merge-trial3-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-Starling-merge-trial3-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-Starling-merge-trial3-7B.Q4_0.gguf	Q4_0	3.83GB
Mistral-Starling-merge-trial3-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-Starling-merge-trial3-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-Starling-merge-trial3-7B.Q4_K.gguf	Q4_K	4.07GB
Mistral-Starling-merge-trial3-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-Starling-merge-trial3-7B.Q4_1.gguf	Q4_1	4.24GB
Mistral-Starling-merge-trial3-7B.Q5_0.gguf	Q5_0	4.65GB
Mistral-Starling-merge-trial3-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-Starling-merge-trial3-7B.Q5_K.gguf	Q5_K	4.78GB
Mistral-Starling-merge-trial3-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-Starling-merge-trial3-7B.Q5_1.gguf	Q5_1	5.07GB
Mistral-Starling-merge-trial3-7B.Q6_K.gguf	Q6_K	5.53GB
Mistral-Starling-merge-trial3-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model:

Nexusflow/Starling-LM-7B-beta
grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B library_name: transformers tags:
mergekit
merge license: apache-2.0

Mistral-Starling-merge-trial3-7B

This is a merge of pre-trained language models created using mergekit. The goal was to combine strong reasoning with 32K context length.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
        layer_range: [0, 32]
      - model: Nexusflow/Starling-LM-7B-beta
        layer_range: [0, 32]
# or, the equivalent models: syntax:
# models:
merge_method: slerp
base_model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
parameters:
  t:
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

RichardErkhov/grimjim_-_Mistral-Starling-merge-trial3-7B-gguf