Fix Mergekit yaml file

#10
by Autumnlight - opened

A buddy and I are trying to apply some magic onto this mode, could it be possible to update the mergekit.yaml so its valid?
Fixed it, it was in line 1314, bonsai, not bonsair

name: new-dawn-llama3-70b-v0.13.2
models:
  - model: bosonai/Higgs-Llama-3-70B
  - model: turboderp/Cat-Llama-3-70B-instruct
merge_method: slerp
base_model: bosonai/Higgs-Llama-3-70B
parameters:
  t:
    - value: 0.2
dtype: float16
---
name: new-dawn-llama3-70b-v0.14 
models:
  - model: bosonai/Higgs-Llama-3-70B
  - model: abacusai/Smaug-Llama-3-70B-Instruct
merge_method: slerp
base_model: bosonai/Higgs-Llama-3-70B
parameters:
  t:
    - value: 0.5
dtype: float16
---
name: new-dawn-llama3-70b-v0.15
models:
  - model: new-dawn-llama3-70b-v0.13.2
  - model: new-dawn-llama3-70b-v0.14
merge_method: slerp
base_model: new-dawn-llama3-70b-v0.13.2
parameters:
  t:
    - value: 0.5
dtype: float16
---
name: new-dawn-llama3-70b-v0.16
models:
  - model: Sao10K/L3-70B-Euryale-v2.1
  - model: new-dawn-llama3-70b-v0.15
merge_method: slerp
base_model: new-dawn-llama3-70b-v0.15
parameters:
  t:
    - value: 0.4
dtype: float16
---
# See https://huggingface.co/jukofyork/Dark-Miqu-70B/discussions/3
# Credit for merge recipe belongs to jukofyork
name: new-dawn-llama3-70b-v0.16-32K
merge_method: linear
models:
  - model: abacusai/Smaug-Llama-3-70B-Instruct-32K
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: up_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - value: 1
  - model: new-dawn-llama3-70b-v0.16
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: up_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - value: 0
base_model: abacusai/Smaug-Llama-3-70B-Instruct-32K
tokenizer_source: base
dtype: float16
---
name: _1-Smaug-bonsai-slerp
models:
  - model: abacusai/Smaug-Llama-3-70B-Instruct-32K
  - model: bosonai/Higgs-Llama-3-70B
merge_method: slerp
base_model: abacusai/Smaug-Llama-3-70B-Instruct-32K
parameters:
  t:
    - value: 0.6
dtype: float16
---
name: _2-Smaug-euryale-slerp
models:
  - model: abacusai/Smaug-Llama-3-70B-Instruct-32K
  - model: Sao10K/L3-70B-Euryale-v2.1
merge_method: slerp
base_model: abacusai/Smaug-Llama-3-70B-Instruct-32K
parameters:
  t:
    - value: 0.65
dtype: float16
---
name: _3-Smaug-bonsai_Smaug-euryale-slerp
models:
  - model: _1-Smaug-bonsai-slerp
  - model: _2-Smaug-euryale-slerp
merge_method: slerp
base_model: _1-Smaug-bonsai-slerp
parameters:
  t:
    - value: 0.5
dtype: float16
---
# See https://huggingface.co/jukofyork/Dark-Miqu-70B/discussions/3
# Credit for merge recipe belongs to jukofyork
name: new-dawn-llama3-70b-v0.18-32K
merge_method: linear
models:
  - model: abacusai/Smaug-Llama-3-70B-Instruct-32K
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: up_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - value: 1
  - model: _3-Smaug-bonsai_Smaug-euryale-slerp
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: up_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - value: 0
base_model: abacusai/Smaug-Llama-3-70B-Instruct-32K
tokenizer_source: base
dtype: float16
---
name: new-dawn-llama3-70b-32K-v1.0
models:
  - model: new-dawn-llama3-70b-v0.16-32K
  - model: new-dawn-llama3-70b-v0.18-32K
merge_method: slerp
base_model: new-dawn-llama3-70b-v0.16-32K
parameters:
  t:
    - value: 0.5
dtype: float16

Sign up or log in to comment