QwQ-slerp1

1
—
by
mergekit-community
Language Model
OTHER
32B params
New
1 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
72GB+ 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
30GB+ RAM

Code Examples

Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
Configurationyaml
merge_method:        slerp
base_model:          Qwen/Qwen2.5-32B-Instruct
tokenizer_source:    Qwen/Qwen2.5-32B-Instruct
dtype:               bfloat16
out_dtype:           bfloat16
parameters:         
  int8_mask:         true
  normalize:         true
  rescale:           false
  t:
    - value:         0.50
slices:
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 0, 8 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 8, 16 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 8, 16 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 16, 24 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 16, 24 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 24, 32 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
      - model:       Qwen/QwQ-32B
        layer_range: [ 32, 40 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 40, 48 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 40, 48 ]
  - sources:
      - model:       Qwen/QwQ-32B
        layer_range: [ 48, 56 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 48, 56 ]
  - sources:
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]
      - model:       Qwen/Qwen2.5-32B-Instruct
        layer_range: [ 56, 64 ]

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.