merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
      layer_range: [0, 8]
  - sources:
    - model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
      layer_range: [8, 24]
      parameters:
        scale:
          - filter: q_proj
            value: 0.919
          - filter: k_proj
            value: 0.919
          - value: 1.0
  - sources:
    - model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
      layer_range: [16, 24]
      parameters:
        scale:
          - filter: q_proj
            value: 0.7
          - filter: k_proj
            value: 0.7
          - filter: o_proj
            value: 0.0
          - filter: down_proj
            value: 0.0
          - value: 1.0
  - sources:
    - model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
      layer_range: [16, 32]
      parameters:
        scale:
          - filter: q_proj
            value: 0.919
          - filter: k_proj
            value: 0.919
          - value: 1.0
  - sources:
    - model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
      layer_range: [32, 40]
merge_method: passthrough
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 18.13
IFEval (0-Shot) 18.69
BBH (3-Shot) 44.27
MATH Lvl 5 (4-Shot) 0.00
GPQA (0-shot) 2.68
MuSR (0-shot) 5.53
MMLU-PRO (5-shot) 37.57
Downloads last month
40
Safetensors
Model size
17B 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 synergetic/FrankenQwen2.5-14B

Base model

Qwen/Qwen2.5-14B
Finetuned
(3)
this model
Quantizations
1 model

Evaluation results