Q2.5-Qwetiapin-32B

8
3
32.0B
—
by
Nohobby
Language Model
OTHER
32B params
New
8 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
72GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
30GB+ RAM

Code Examples

Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Merge Detailsyaml
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
  epsilon: 0.4 #was supposed to be 0.04 
  lambda: 1.1
base_model: allura-org/Qwen2.5-32b-RP-Ink
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: allura-org/Qwen2.5-32b-RP-Ink
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step2yaml
models:
  - model: Aryanne/QwentileSwap
    parameters:
      weight: [1.0, 0.9, 0.8, 0.9, 1.0]
  - model: Daemontatox/Cogito-Ultima
    parameters:
      weight: [0, 0.1, 0.2, 0.1, 0]
merge_method: nuslerp
parameters:
  nuslerp_row_wise: true
dtype: bfloat16
tokenizer_source: base
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16
Step3yaml
models:
  - model: Step2
  - model: Step1
merge_method: sce
base_model: Step2
parameters:
  select_topk:
    - value: [0.3, 0.35, 0.4, 0.35, 0.2]
dtype: bfloat16

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.