Qwen2.5-1.5B-THREADRIPPER-v0.1

2
1.5B
—
by
Xiaojian9992024
Language Model
OTHER
1.5B params
New
2 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
4GB+ RAM
Mobile
Laptop
Server
Quick Summary

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

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2GB+ RAM

Code Examples

Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
Configurationyaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.