ChatWaifu_22B_v2.0_preview

Name: ChatWaifu_22B_v2.0_preview
Rating: 8.7 (10 reviews)
Author: spow12

22.0B

2 languages

license:cc-by-nc-4.0

spow12

Language Model

OTHER

22B params

New

3 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

50GB+ RAM

Mobile

Laptop

Server

Quick Summary

This model aimed to act like visual novel character.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

21GB+ RAM

Code Examples

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
dtype: bfloat16

Merge Formatyaml

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
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 # fallback for rest of tensors
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.