CoolFace
Modelpublic

RichardErkhov/flammenai_-_flammen9-mistral-7B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes2kdownloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

flammen9-mistral-7B - GGUF

  • —Model creator: https://huggingface.co/flammenai/
  • —Original model: https://huggingface.co/flammenai/flammen9-mistral-7B/
NameQuant methodSize
flammen9-mistral-7B.Q2_K.ggufQ2_K2.53GB
flammen9-mistral-7B.IQ3_XS.ggufIQ3_XS2.81GB
flammen9-mistral-7B.IQ3_S.ggufIQ3_S2.96GB
flammen9-mistral-7B.Q3_K_S.ggufQ3KS2.95GB
flammen9-mistral-7B.IQ3_M.ggufIQ3_M3.06GB
flammen9-mistral-7B.Q3_K.ggufQ3_K3.28GB
flammen9-mistral-7B.Q3_K_M.ggufQ3KM3.28GB
flammen9-mistral-7B.Q3_K_L.ggufQ3KL3.56GB
flammen9-mistral-7B.IQ4_XS.ggufIQ4_XS3.67GB
flammen9-mistral-7B.Q4_0.ggufQ4_03.83GB
flammen9-mistral-7B.IQ4_NL.ggufIQ4_NL3.87GB
flammen9-mistral-7B.Q4_K_S.ggufQ4KS3.86GB
flammen9-mistral-7B.Q4_K.ggufQ4_K4.07GB
flammen9-mistral-7B.Q4_K_M.ggufQ4KM4.07GB
flammen9-mistral-7B.Q4_1.ggufQ4_14.24GB
flammen9-mistral-7B.Q5_0.ggufQ5_04.65GB
flammen9-mistral-7B.Q5_K_S.ggufQ5KS4.65GB
flammen9-mistral-7B.Q5_K.ggufQ5_K4.78GB
flammen9-mistral-7B.Q5_K_M.ggufQ5KM4.78GB
flammen9-mistral-7B.Q5_1.ggufQ5_15.07GB
flammen9-mistral-7B.Q6_K.ggufQ6_K5.53GB
flammen9-mistral-7B.Q8_0.ggufQ8_07.17GB

Original model description: --- license: apache-2.0 base_model:

  • —nbeerbower/flammen5-mistral-7B
  • —nbeerbower/flammen8-mistral-7B
  • —nbeerbower/flammen3X library_name: transformers tags:
  • —mergekit
  • —merge

flammen9-mistral-7B

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using nbeerbower/flammen8-mistral-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml
models:
  - model: nbeerbower/flammen8-mistral-7B
  - model: nbeerbower/flammen5-mistral-7B
    parameters:
      density: 0.5
      weight: 0.5
  - model: nbeerbower/flammen3X
    parameters:
      density: 0.5
      weight: 0.3
merge_method: dare_ties
base_model: nbeerbower/flammen8-mistral-7B
parameters:
  normalize: true
dtype: bfloat16