Edit model card

merge

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:

slices:
- sources:
  - layer_range: [0, 10]
    model: deepseek-ai/deepseek-llm-67b-base
- sources:
  - layer_range: [20, 30]
    model: deepseek-ai/deepseek-llm-67b-base
- sources:
  - layer_range: [30, 40]
    model: deepseek-ai/deepseek-llm-67b-base
- sources:
  - layer_range: [40, 50]
    model: deepseek-ai/deepseek-llm-67b-base
- sources:
  - layer_range: [50, 60]
    model: deepseek-ai/deepseek-llm-67b-base
- sources:
  - layer_range: [60, 65]
    model: deepseek-ai/deepseek-llm-67b-base
merge_method: passthrough
dtype: float16
Downloads last month
1
Safetensors
Model size
39.7B params
Tensor type
FP16
·

Finetuned from