DeepSeek-R1-0528-Qwen3-8B-remap

2
8.0B
—
by
djuna
Language Model
OTHER
8B params
New
2 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
18GB+ 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
8GB+ RAM

Code Examples

Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16
Configurationyaml
models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
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.