Update README.md

README.md

@@ -1,30 +1,249 @@
 ---
-base_model:
-- d-rang-d/MS3-megamerge
-- unsloth/Mistral-Small-24B-Instruct-2501
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- unsloth/Mistral-Small-24B-Base-2501
+- unsloth/Mistral-Small-24B-Instruct-2501
+- trashpanda-org/MS-24B-Instruct-Mullein-v0
+- trashpanda-org/Llama3-24B-Mullein-v1
+- ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
+- TheDrummer/Cydonia-24B-v2
+- estrogen/MS2501-24b-Ink-apollo-ep2
+- huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
+- ToastyPigeon/ms3-roselily-rp-v2
+- PocketDoc/Dans-DangerousWinds-V1.1.1-24b
+- ReadyArt/Forgotten-Safeword-24B-V2.2
+- PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
+- Undi95/MistralThinker-e2
+- lemonilia/Mistral-Small-3-Reasoner-s1
+- arcee-ai/Arcee-Blitz
+- SicariusSicariiStuff/Redemption_Wind_24B
 ---
-# merge
+***
+## Tantum
+
+>Everything is edible if you are brave enough
+
+![Так и живём](https://files.catbox.moe/ergq6n.png)
+
+### Overview
+
+It's kind of hard to judge a 24B model after using a 70B for a while. From some tests, I think it might be better than my ms-22B and qwen-32B merges.
+
+It has some prose, some character adherence, and... `<think>` tags! It will consistently think if you add `<think>` tag as prefill, tho I think it will obviously not think as well as an actual thinking model distill.
+
+**Settings:**
+
+Samplers: [Weird preset](https://files.catbox.moe/ccwmca.json) | [Mullein preset](https://files.catbox.moe/0pkv2j.json)
+
+Prompt format: Mistral-V7 (?)
+
+ChatML and Llama3 give better results imo. In the case of ChatML, there are Dans-PersonalityEngine and Redemption-Wind models that have been trained on it. But Llama3? No clue.
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+I use [this](https://files.catbox.moe/daluze.json) lorebook for all chats instead of a system prompt for mistal models.
+
+### Quants
+
+[5_K_S](https://huggingface.co/Nohobby/ignore_MS3-test-Q5_K_S-GGUF/resolve/main/ignore_ms3-test-q5_k_s.gguf?download=true)
+
+***
 
 ## Merge Details
-### Merge Method
+### Merging steps
+
+## MS3-test-Merge-1
+
+```yaml
+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
+```
+
+```yaml
+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
 
-This model was merged using the [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [d-rang-d/MS3-megamerge](https://huggingface.co/d-rang-d/MS3-megamerge) as a base.
+```
 
-### Models Merged
+Some early MS3 merge. Not really worth using on its own. Just added it for fun.
 
-The following models were included in the merge:
-* [unsloth/Mistral-Small-24B-Instruct-2501](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501)
+## RP-half1
 
-### Configuration
+```yaml
+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
+```
 
-The following YAML configuration was used to produce this model:
+## RP-half2
+
+```yaml
+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-whole
+
+```yaml
+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
+```
+
+## INT
+
+```yaml
+merge_method: della_linear
+dtype: bfloat16
+parameters:
+  normalize: true
+  int8_mask: true
+tokenizer:
+ source: base
+base_model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
+models:
+    - model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: Undi95/MistralThinker-e2
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: d-rang-d/ignore_MS3-Reasoner-mergekit
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: arcee-ai/Arcee-Blitz
+      parameters:
+        density: 0.55
+        weight: 1
+```
+
+## Tantumv00
+
+```yaml
+output_base_model: "SicariusSicariiStuff/Redemption_Wind_24B"
+output_dtype: "bfloat16"
+finetune_merge:
+  - { "model": "mergekit-community/MS3-INT", "base": "unsloth/Mistral-Small-24B-Instruct-2501", "alpha": 1.0, "is_input": true }
+  - { "model": "mergekit-community/MS-RP-whole", "base": "unsloth/Mistral-Small-24B-Instruct-2501", "alpha": 0.7, "is_output": true }
+output_dir: "output_model"
+device: "cpu"
+clean_cache: false
+cache_dir: "cache"
+storage_dir: "storage"
+```
+
+Doesn't look like a mergekit recipe, right? Well, it's not. It's for a standalone merge tool: https://github.com/54rt1n/shardmerge
+
+If you want to use it for something non-qwen you can replace index.py with [this](https://files.catbox.moe/bgxmuz.py) and writer.py with [that](https://files.catbox.moe/ewww39.py). A much better solution is possible, ofc, but I'm a dumdum and can't code. The creator knows about this issue and will fix it... Someday, I guess.
+
+You also need to know that this thing is *really* slow, and it took me 5 hours to cram 3 24B models together.
+
+## Tantumv01
 
 ```yaml
 dtype: bfloat16
@@ -63,5 +282,4 @@ models:
         - filter: down_proj
           value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
         - value: 1
-
-```
+```