Nitral-Archive/HerculeanSea-7b-128k

Thanks to bartowski we have /HerculeanSea-7b-128k-exl2 https://huggingface.co/bartowski/HerculeanSea-7b-128k-exl2

Models Merged

The following models were included in the merge:

• Test157t/Pasta-Sea-7b-128k
• Locutusque/Hercules-2.0-Mistral-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Test157t/Pasta-Sea-7b-128k
        layer_range: [0, 32]
      - model: Locutusque/Hercules-2.0-Mistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Pasta-Sea-7b-128k
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: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.53
AI2 Reasoning Challenge (25-Shot)	66.21
HellaSwag (10-Shot)	85.80
MMLU (5-Shot)	64.28
TruthfulQA (0-shot)	55.77
Winogrande (5-shot)	80.74
GSM8k (5-shot)	58.38