WesPro/Llama3-OrpoSmaug-Slerp-8B

Thanks to mradermacher, there are also GGUF quants (Q2_K-Q8_K & IQ3_XS-IQ4_XS) for this model available here: https://huggingface.co/mradermacher/Llama3-OrpoSmaug-Slerp-8B-GGUF

---

base_model: [] library_name: transformers tags:

• mergekit
• merge

---

Llama3 Orpo Smaug - Slerp

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:

• H:\merge\Llama-3-Smaug-8B
• H:\merge\OrpoLlama-3-8b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: H:\merge\Llama-3-Smaug-8B
        layer_range: [0, 32]
      - model: H:\merge\OrpoLlama-3-8b
        layer_range: [0, 32]
merge_method: slerp
base_model: H:\merge\Llama-3-Smaug-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16