Edit model card

codellama-7B-instruct-passthrough

codellama-7B-instruct-passthrough is a merge of the following models using mergekit:

🧩 Configuration

slices:
  - sources:
    - model: tyson0420/alpaca_codellama
      layer_range: [0, 32]
  - sources:
    - model: tyson0420/stack-codellama-fil-python
      layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16
Downloads last month
1
Safetensors
Model size
8.36B params
Tensor type
BF16
·