llama-3.1-8b-mixed-slerp-0.90

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• /scratch/gpfs/vv7118/models/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b
• /scratch/gpfs/vv7118/models/hub/models--deepseek-ai--DeepSeek-R1-Distill-Llama-8B/snapshots/ebf7e8d03db3d86a442d22d30d499abb7ec27bea

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /scratch/gpfs/vv7118/models/hub/models--deepseek-ai--DeepSeek-R1-Distill-Llama-8B/snapshots/ebf7e8d03db3d86a442d22d30d499abb7ec27bea
merge_method: slerp
base_model: /scratch/gpfs/vv7118/models/hub/models--meta-llama--Llama-3.1-8B/snapshots/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b
parameters:
  t:
    - value: 0.9 # fallback for rest of tensors
dtype: float16
chat_template: "llama3" 

tokenizer:
  source: "union"  # or "base" or a specific model path