Edit model card

Lumiere-120b

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

Quants

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
parameters:
  weight: 1.0
slices:
  - sources:
      - model: Undi95/Miqu-70B-Alpaca-DPO
        layer_range: [0, 1]
      - model: Sao10K/Euryale-1.3-L2-70B
        layer_range: [0, 1]
        parameters:
          weight: 0
  - sources:
      - model: Undi95/Miqu-70B-Alpaca-DPO
        layer_range: [1, 20]
  - sources:
      - model: Sao10K/Euryale-1.3-L2-70B
        layer_range: [10, 30]
  - sources:
      - model: Undi95/Miqu-70B-Alpaca-DPO
        layer_range: [20, 40]
  - sources:
      - model: Sao10K/Euryale-1.3-L2-70B
        layer_range: [30, 50]
  - sources:
      - model: Undi95/Miqu-70B-Alpaca-DPO
        layer_range: [40, 60]
  - sources:
      - model: Sao10K/Euryale-1.3-L2-70B
        layer_range: [50, 70]
  - sources:
      - model: Undi95/Miqu-70B-Alpaca-DPO
        layer_range: [60, 79]
  - sources:
      - model: Undi95/Miqu-70B-Alpaca-DPO
        layer_range: [79, 80]
      - model: Sao10K/Euryale-1.3-L2-70B
        layer_range: [79, 80]
        parameters:
          weight: 0
dtype: float16
tokenizer_source: model:Undi95/Miqu-70B-Alpaca-DPO
Downloads last month
3
Safetensors
Model size
120B params
Tensor type
FP16
·
Inference Examples
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 bcse/Lumiere-120b

Merge model
this model
Quantizations
2 models