RichardErkhov/gqd_-_mistral-merge-7b-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-merge-7b - GGUF

• Model creator: https://huggingface.co/gqd/
• Original model: https://huggingface.co/gqd/mistral-merge-7b/

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

Original model description:

base_model: - teknium/OpenHermes-2.5-Mistral-7B - Open-Orca/Mistral-7B-SlimOrca tags: - mergekit - merge license: unlicense

out2

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:

• teknium/OpenHermes-2.5-Mistral-7B
• Open-Orca/Mistral-7B-SlimOrca

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
dtype: float16
models:
        - model: teknium/OpenHermes-2.5-Mistral-7B
          parameters:
                weight: 1.0
        - model: Open-Orca/Mistral-7B-SlimOrca
          parameters:
                weight: 1.0
#tokenizer_source: union