Bagel-Hermes-34B-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:

  • Nous-Hermes-2-Yi-34B
  • bagel-dpo-34b-v0.2
  • nontoxic-bagel-34b-v0.2

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
      - model: bagel-dpo-34b-v0.2
        layer_range: [0, 60]
      - model: Nous-Hermes-2-Yi-34B
        layer_range: [0, 60]

merge_method: slerp
base_model: nontoxic-bagel-34b-v0.2

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
tokenizer_source: union
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 75.24
AI2 Reasoning Challenge (25-Shot) 70.73
HellaSwag (10-Shot) 85.68
MMLU (5-Shot) 77.29
TruthfulQA (0-shot) 67.09
Winogrande (5-shot) 84.37
GSM8k (5-shot) 66.26

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 27.06
IFEval (0-Shot) 46.03
BBH (3-Shot) 41.96
MATH Lvl 5 (4-Shot) 4.91
GPQA (0-shot) 11.30
MuSR (0-shot) 17.01
MMLU-PRO (5-shot) 41.15
Downloads last month
3,824
Safetensors
Model size
34.4B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Weyaxi/Bagel-Hermes-34B-Slerp

Merges
1 model
Quantizations
3 models

Space using Weyaxi/Bagel-Hermes-34B-Slerp 1

Evaluation results