Qwen2.5-14B-YOYO-V4

Qwen2.5-YOYO Fourth-Gen Model Officially Released!

Key Highlights:

1. Richer Knowledge & Improved Instruction Compliance

2. Integrated Code Model and R1 Distillation for Improved Coding/Reasoning

3. 1M-Token Long Context Window

First stage:

merge_method: sce  
models:
  # Pivot model
  - model: Qwen/Qwen2.5-14B-Instruct-1M
  # Target models  
  - model: Qwen/Qwen2.5-14B  
base_model: Qwen/Qwen2.5-14B-Instruct-1M  
parameters:  
  select_topk: 1  
dtype: bfloat16  
tokenizer_source: base  
normalize: true  
int8_mask: true  
name: Qwen2.5-14B-1M

models:  
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9  
merge_method: della  
base_model: Qwen2.5-14B-1M  
parameters:  
  density: 1  
  weight: 1  
  lambda: 0.9  
  normalize: true  
  int8_mask: true  
dtype: bfloat16  
tokenizer_source: base  
name: Qwen2.5-14B-1M-della

Second stage:

models:  
  - model: Qwen/Qwen2.5-14B-Instruct  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9
  - model: Qwen/Qwen2.5-14B-Instruct-1M  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9  
merge_method: della  
base_model: arcee-ai/Virtuoso-Small-v2  
parameters:  
  density: 1  
  weight: 1  
  lambda: 0.9  
  normalize: true  
  int8_mask: true  
dtype: bfloat16  
tokenizer_source: base  
name: Qwen2.5-14B-YOYO-della1

models:  
  - model: Qwen/Qwen2.5-14B-Instruct  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9
  - model: Qwen/Qwen2.5-14B-Instruct-1M  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9  
merge_method: della  
base_model: arcee-ai/SuperNova-Medius  
parameters:  
  density: 1  
  weight: 1  
  lambda: 0.9  
  normalize: true  
  int8_mask: true  
dtype: bfloat16  
tokenizer_source: base  
name: Qwen2.5-14B-YOYO-della2

models:  
  - model: Qwen/Qwen2.5-14B-Instruct  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9
  - model: Qwen/Qwen2.5-14B-Instruct-1M  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9  
merge_method: della  
base_model: Azure99/Blossom-V6-14B  
parameters:  
  density: 1  
  weight: 1  
  lambda: 0.9  
  normalize: true  
  int8_mask: true  
dtype: bfloat16  
tokenizer_source: base  
name: Qwen2.5-14B-YOYO-della3

Third stage:

Step 1:

models:  
  - model: Qwen/Qwen2.5-Coder-14B-Instruct  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9  
merge_method: della  
base_model: Qwen/Qwen2.5-Coder-14B  
parameters:  
  density: 1  
  weight: 1  
  lambda: 0.9  
  normalize: true  
  int8_mask: true  
dtype: bfloat16  
tokenizer_source: base  
name: Qwen2.5-Coder-14B-della

Step 2:

merge_method: model_stock  
base_model: Qwen/Qwen2.5-14B-Instruct  
models:  
  - model: Qwen2.5-Coder-14B-della  
  - model: arcee-ai/Virtuoso-Small-v2  
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B  
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2  
dtype: bfloat16  
tokenizer_source: base  
int8_mask: true  
normalize: true  
name: Qwen2.5-14B-mst

Final stage:

merge_method: model_stock  
base_model: Qwen2.5-14B-1M-della  
models:  
  - model: Qwen2.5-14B-della1  
  - model: Qwen2.5-14B-della2  
  - model: Qwen2.5-14B-della3  
  - model: Qwen2.5-14B-mst  
dtype: bfloat16  
tokenizer_source: base  
int8_mask: true  
normalize: true  
name: YOYO-AI/Qwen2.5-14B-YOYO-V4