Overview
One of the merging steps for Tantum. Might be better than the end result
Model files may not be downloadable
You can get full-weight files from here: https://huggingface.co/mergekit-community/MS-RP-whole
This happened because I was using the mergekit-gui space for merging and got lazy about manually dragging the intermediate steps to my org, so I just set it to upload to mergekit-community. When I learned that this thing was usable on it's own, I decided to add some info to the model card and duplicated the repo here before linking it in the Tantum readme file.
yeah
Settings:
Samplers: Weird preset | Forgotten-Safeword preset
Prompt format: Mistral-V7-Tekken (?)
I use this lorebook for all chats instead of a system prompt for mistal models.
Quants
Merge Details
Merging steps
MS3-test-Merge-1
models:
- model: unsloth/Mistral-Small-24B-Base-2501
- model: unsloth/Mistral-Small-24B-Instruct-2501+ToastyPigeon/new-ms-rp-test-ws
parameters:
select_topk:
- value: [0.05, 0.03, 0.02, 0.02, 0.01]
- model: unsloth/Mistral-Small-24B-Instruct-2501+estrogen/MS2501-24b-Ink-ep2-adpt
parameters:
select_topk: 0.1
- model: trashpanda-org/MS-24B-Instruct-Mullein-v0
parameters:
select_topk: 0.4
base_model: unsloth/Mistral-Small-24B-Base-2501
merge_method: sce
parameters:
int8_mask: true
rescale: true
normalize: true
dtype: bfloat16
tokenizer_source: base
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
density: 0.55
base_model: Step1
models:
- model: unsloth/Mistral-Small-24B-Instruct-2501
parameters:
weight:
- filter: v_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- filter: o_proj
value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
- filter: up_proj
value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
- filter: gate_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- filter: down_proj
value: [1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
- value: 0
- model: Step1
parameters:
weight:
- filter: v_proj
value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
- filter: o_proj
value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
- filter: up_proj
value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
- filter: gate_proj
value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
- filter: down_proj
value: [0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1]
- value: 1
Some early MS3 merge. Not really worth using on its own. Just added it for fun.
RP-half1
models:
- model: ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
parameters:
weight: 0.2
density: 0.7
- model: trashpanda-org/Llama3-24B-Mullein-v1
parameters:
weight: 0.2
density: 0.7
- model: TheDrummer/Cydonia-24B-v2
parameters:
weight: 0.2
density: 0.7
merge_method: della_linear
base_model: Nohobby/MS3-test-Merge-1
parameters:
epsilon: 0.2
lambda: 1.1
dtype: bfloat16
tokenizer:
source: base
RP-half2
base_model: Nohobby/MS3-test-Merge-1
parameters:
epsilon: 0.05
lambda: 0.9
int8_mask: true
rescale: true
normalize: false
dtype: bfloat16
tokenizer:
source: base
merge_method: della
models:
- model: estrogen/MS2501-24b-Ink-apollo-ep2
parameters:
weight: [0.1, -0.01, 0.1, -0.02, 0.1]
density: [0.6, 0.4, 0.5, 0.4, 0.6]
- model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
parameters:
weight: [0.02, -0.01, 0.02, -0.02, 0.01]
density: [0.45, 0.55, 0.45, 0.55, 0.45]
- model: ToastyPigeon/ms3-roselily-rp-v2
parameters:
weight: [0.01, -0.02, 0.02, -0.025, 0.01]
density: [0.45, 0.65, 0.45, 0.65, 0.45]
- model: PocketDoc/Dans-DangerousWinds-V1.1.1-24b
parameters:
weight: [0.1, -0.01, 0.1, -0.02, 0.1]
density: [0.6, 0.4, 0.5, 0.4, 0.6]
RP-broth/MS-RP-whole
base_model: ReadyArt/Forgotten-Safeword-24B-V2.2
merge_method: model_stock
dtype: bfloat16
models:
- model: mergekit-community/MS3-RP-half1
- model: mergekit-community/MS3-RP-RP-half2