SthenoLlamaStock

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Undi95/Meta-Llama-3-8B-hf as a base.

Models Merged

The following models were included in the merge:

• Sao10K/L3-8B-Stheno-v3.2
• ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
• O1-OPEN/OpenO1-LLama-8B-v0.1

Configuration

The following YAML configuration was used to produce this model:

# Mergekit Configuration for Model Merge

# Base model (primary reference model)
base_model: Undi95/Meta-Llama-3-8B-hf

# Merge method (using TIES for intelligent merging)
merge_method: ties

# Specific model configurations
models:
  - model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      density: 0.4
      weight: 0.25

  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
    parameters:
      density: 0.5
      weight: 0.35

  - model: O1-OPEN/OpenO1-LLama-8B-v0.1
    parameters:
      density: 0.3
      weight: 0.4

# Merge parameters
parameters:
  normalize: true
  int8_mask: true
  dtype: 16  # Explicitly using 16-bit float representation

# Tokenizer source (use base model's tokenizer)
tokenizer_source: base