CoolFace
Modelpublic

RichardErkhov/Dampfinchen_-_Ultra-Instruct-12B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes241downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Ultra-Instruct-12B - GGUF

  • —Model creator: https://huggingface.co/Dampfinchen/
  • —Original model: https://huggingface.co/Dampfinchen/Ultra-Instruct-12B/
NameQuant methodSize
Ultra-Instruct-12B.Q2_K.ggufQ2_K4.46GB
Ultra-Instruct-12B.Q3_K_S.ggufQ3KS5.15GB
Ultra-Instruct-12B.Q3_K.ggufQ3_K5.67GB
Ultra-Instruct-12B.Q3_K_M.ggufQ3KM5.67GB
Ultra-Instruct-12B.Q3_K_L.ggufQ3KL6.11GB
Ultra-Instruct-12B.IQ4_XS.ggufIQ4_XS6.33GB
Ultra-Instruct-12B.Q4_0.ggufQ4_06.59GB
Ultra-Instruct-12B.IQ4_NL.ggufIQ4_NL6.65GB
Ultra-Instruct-12B.Q4_K_S.ggufQ4KS6.63GB
Ultra-Instruct-12B.Q4_K.ggufQ4_K6.96GB
Ultra-Instruct-12B.Q4_K_M.ggufQ4KM6.96GB
Ultra-Instruct-12B.Q4_1.ggufQ4_17.26GB
Ultra-Instruct-12B.Q5_0.ggufQ5_07.93GB
Ultra-Instruct-12B.Q5_K_S.ggufQ5KS7.93GB
Ultra-Instruct-12B.Q5_K.ggufQ5_K8.13GB
Ultra-Instruct-12B.Q5_K_M.ggufQ5KM8.13GB
Ultra-Instruct-12B.Q5_1.ggufQ5_18.61GB
Ultra-Instruct-12B.Q6_K.ggufQ6_K9.37GB
Ultra-Instruct-12B.Q8_0.ggufQ8_012.13GB

Original model description: --- base_model:

  • —Pyroserenus/Orthrus-12b-v0.8
  • —nbeerbower/mistral-nemo-gutenberg-12B-v2
  • —mergekit-community/Deutscher-Pantheon-12B
  • —IntervitensInc/Mistral-Nemo-Base-2407-chatml library_name: transformers tags:
  • —mergekit
  • —merge license: cc-by-nc-4.0 ---

merge

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 IntervitensInc/Mistral-Nemo-Base-2407-chatml 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: mergekit-community/Deutscher-Pantheon-12B
    parameters:
      weight: 0.3
      density: 0.5
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v2
    parameters:
      weight: 0.3
      density: 0.5
  - model: Pyroserenus/Orthrus-12b-v0.8
    parameters:
      weight: 0.6
      density: 0.5
merge_method: dare_ties
base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
dtype: bfloat16
name: Ultra-Instruct-12B

Not responsible for what you do with it. Use with caution. WARNING: UNCENSORED. SMART.

Use ChatML. Note: It appears it has trouble stopping. If you value extremly long replies, this might be the model for you.