ryan0712
/

llama-3-8b-slow-DUS-method-1

Text Generation

Transformers

Safetensors

ryan0712/llama-3-8b-DUS-initialized

ryan0712/llama-3-8b-slow-DUS-layer-SLERP

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

llama-3-8b-slow-DUS-method-1

File size: 323 Bytes

4356f7a


slices:
  - sources:
    - model: ryan0712/llama-3-8b-DUS-initialized
      layer_range: [0, 21]
  - sources:
    - model: ryan0712/llama-3-8b-slow-DUS-layer-SLERP
      layer_range: [0, 1]
  - sources:
    - model: ryan0712/llama-3-8b-DUS-initialized
      layer_range: [21, 48]
merge_method: passthrough
dtype: bfloat16