ZEUS-8B-V29

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using T145/KRONOS-8B-V8 as a base.

Models Merged

The following models were included in the merge:

• Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
• unsloth/Llama-3.1-Storm-8B
• VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
• arcee-ai/Llama-3.1-SuperNova-Lite

Configuration

The following YAML configuration was used to produce this model:

base_model: T145/KRONOS-8B-V8
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
  random_seed: 145.0
slices:
- sources:
  - layer_range: [0, 32]
    model: unsloth/Llama-3.1-Storm-8B
    parameters:
      density: 0.94
      weight: 0.35
  - layer_range: [0, 32]
    model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      density: 0.92
      weight: 0.26
  - layer_range: [0, 32]
    model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
    parameters:
      density: 0.91
      weight: 0.2
  - layer_range: [0, 32]
    model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.93
      weight: 0.19
  - layer_range: [0, 32]
    model: T145/KRONOS-8B-V8
tokenizer:
  tokens:
    <|begin_of_text|>:
      force: true
      source: T145/KRONOS-8B-V8
    <|eot_id|>:
      force: true
      source: T145/KRONOS-8B-V8
    <|finetune_right_pad_id|>:
      force: true
      source: T145/KRONOS-8B-V8

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	28.83
IFEval (0-Shot)	74.18
BBH (3-Shot)	32.35
MATH Lvl 5 (4-Shot)	14.27
GPQA (0-shot)	10.18
MuSR (0-shot)	9.53
MMLU-PRO (5-shot)	32.45