llama3.2-typhoon-passthrough

llama3.2-typhoon-passthrough is a merge of the following models using mergekit:

meta-llama/Llama-3.2-3B-Instruct
scb10x/llama3.2-typhoon2-3b-instruct

🧩 Configuration

slices:
  - sources:
    - model: meta-llama/Llama-3.2-3B-Instruct
      layer_range: [0, 28]
  - sources:
    - model: scb10x/llama3.2-typhoon2-3b-instruct
      layer_range: [20, 28]
merge_method: passthrough
dtype: bfloat16

Downloads last month: 5

Safetensors

Model size

4.02B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.