merged

Use v1!

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:

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
- sources:
  - layer_range: [8, 16]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
    parameters:
      scale:
      - filter: o_proj
        value: 0.5
      - filter: down_proj
        value: 0.5
      - filter: q_proj
        value: 0.85355339059
      - filter: k_proj
        value: 0.85355339059
      - value: 1.0
- sources:
  - layer_range: [8, 16]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
    parameters:
      scale:
      - filter: q_proj
        value: 0.85355339059
      - filter: k_proj
        value: 0.85355339059
      - value: 1.0
- sources:
  - layer_range: [16, 17]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
- sources:
  - layer_range: [17, 24]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
    parameters:
      scale:
      - filter: o_proj
        value: 0.5
      - filter: down_proj
        value: 0.5
      - filter: q_proj
        value: 0.85355339059
      - filter: k_proj
        value: 0.85355339059
      - value: 1.0
- sources:
  - layer_range: [17, 24]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
    parameters:
      scale:
      - filter: q_proj
        value: 0.85355339059
      - filter: k_proj
        value: 0.85355339059
      - value: 1.0
- sources:
  - layer_range: [24, 25]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
- sources:
  - layer_range: [25, 32]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
    parameters:
      scale:
      - filter: o_proj
        value: 0.5
      - filter: down_proj
        value: 0.5
      - filter: q_proj
        value: 0.85355339059
      - filter: k_proj
        value: 0.85355339059
      - value: 1.0
- sources:
  - layer_range: [25, 32]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
    parameters:
      scale:
      - filter: q_proj
        value: 0.85355339059
      - filter: k_proj
        value: 0.85355339059
      - value: 1.0
- sources:
  - layer_range: [32, 40]
    model: nvidia/Mistral-NeMo-Minitron-8B-Base
Downloads last month
2
Safetensors
Model size
12.5B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for nlpguy/Mistral-NeMo-Minitron-Upscale-v2

Finetuned
(14)
this model
Quantizations
2 models