Qwen3-8B-YOYO-slerp

Name: Qwen3-8B-YOYO-slerp
Author: YOYO-AI

8.0B

2 languages

license:apache-2.0

YOYO-AI

Language Model

OTHER

8B params

New

30 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

18GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

8GB+ RAM

Code Examples

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_dtype: bfloat16

*Parameter Settings*:yaml

slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: Qwen/Qwen3-8B
        layer_range: [0, 36]
merge_method: slerp
base_model: Qwen/Qwen3-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
tokenizer_source: base
dtype: float32
out_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.