Edit model card

Danish-Swedish Merged Model

This is a merge of the following models, all based on mistralai/Mistral-7B-v0.1:

  1. danish-foundation-models/munin-7b-alpha, continued pretraining on Danish data;
  2. timpal0l/Mistral-7B-v0.1-flashback-v2, continued pretraining on Swedish data.

Model Details

  • Merged by: Dan Saattrup Nielsen
  • Model type: Decoder model, based on mistralai/Mistral-7B-v0.1
  • Language(s): Danish and Swedish
  • License: CC-BY-4.0
  • Merge configuration:
    dict(
        models=[
            dict(
                model="danish-foundation-models/munin-7b-alpha",
                parameters=dict(
                    weight=1.0,
                    density=0.6,
                ),
            ),
            dict(
                model="timpal0l/Mistral-7B-v0.1-flashback-v2",
                parameters=dict(
                    weight=1.0,
                    density=0.6,
                ),
            ),
        ],
        merge_method="dare_ties",
        random_seed=4242
        base_model="mistralai/Mistral-7B-v0.1",
        parameters=dict(
            int8_mask=True,
            normalize=True,
        ),
        dtype="bfloat16",
    )
    
Downloads last month
10
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for merge-crew/da-sv-dare-ties-density-0.6