DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct

MN-magnum-v2.5-18.5B-kto-Instruct

This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.

For full information about this model, including:

• Details about this model and its use case(s).
• Context limits
• Special usage notes / settings.
• Any model(s) used to create this model.
• Template(s) used to access/use this model.
• Example generation(s)
• GGUF quants of this model

Please go to:

[ https://huggingface.co/DavidAU/MN-Magnum-v2.5-18.5B-kto-Story-Wizard-ED1-Instruct-GGUF ]

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• G:/11B/magnum-v2.5-12b-kto
• g:/11b/Mistral-Nemo-Instruct-2407-12B

Configuration

The following YAML configuration was used to produce this model:

# SMB with instruct to help performance.

slices:
 - sources:
   - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
     layer_range: [0, 14]
 - sources:
   - model: G:/11B/magnum-v2.5-12b-kto
     layer_range: [8, 24]
     parameters:
       scale:
         - filter: o_proj
           value: 1
         - filter: down_proj
           value: 1
         - value: 1
 - sources:
   - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
     layer_range: [14, 22]
     parameters:
       scale:
         - filter: o_proj
           value: .5
         - filter: down_proj
           value: .5
         - value: 1
 - sources:
   - model: g:/11b/Mistral-Nemo-Instruct-2407-12B
     layer_range: [22, 31]
     parameters:
       scale:
         - filter: o_proj
           value: .75
         - filter: down_proj
           value: .75
         - value: 1
 - sources:
   - model: G:/11B/magnum-v2.5-12b-kto
     layer_range: [24, 40]
     parameters:
       scale:
         - filter: o_proj
           value: 1
         - filter: down_proj
           value: 1
         - value: 1
merge_method: passthrough
dtype: bfloat16