Update README.md

README.md

@@ -1,29 +1,150 @@
 ---
 base_model:
 - unsloth/Mistral-Small-Instruct-2409
+- TheDrummer/Cydonia-22B-v1.2
+- Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
+- anthracite-org/magnum-v4-22b
+- ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
+- spow12/ChatWaifu_v2.0_22B
+- rAIfle/Acolyte-22B
+- Envoid/Mistral-Small-NovusKyver
+- InferenceIllusionist/SorcererLM-22B
+- allura-org/MS-Meadowlark-22B
+- crestf411/MS-sunfall-v0.7.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+license: other
+language:
+- en
 ---
-# Schisandra-22B-v0.2
+***
+## Schisandra
+
+Many thanks to the authors of the models used!
+
+[RPMax v1.1](https://huggingface.co/ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1) | [Pantheon-RP](https://huggingface.co/Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small) | [UnslopSmall-v1](https://huggingface.co/TheDrummer/UnslopSmall-22B-v1) | [Magnum V4](https://huggingface.co/anthracite-org/magnum-v4-22b) | [ChatWaifu v2.0](https://huggingface.co/spow12/ChatWaifu_v2.0_22B) | [SorcererLM](https://huggingface.co/InferenceIllusionist/SorcererLM-22B) | [Acolyte](https://huggingface.co/rAIfle/Acolyte-22B) | [NovusKyver](https://huggingface.co/Envoid/Mistral-Small-NovusKyver) | (Meadowlark)[https://huggingface.co/allura-org/MS-Meadowlark-22B] | (Sunfall)[https://huggingface.co/crestf411/MS-sunfall-v0.7.0] 
+***
+
+### Overview
+
+Main uses: RP, Storywriting
+
+An intelligent model that is attentive to details and has a low-slop writing style. This time with a stable tokenizer.
+
+Oh, and it now contains 10 finetunes! Not sure if some of them actually contribute to the output, but it's nice to see the numbers growing.
+
+***
+
+### Quants
+
+GGUF: [Static](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.2-GGUF) | [Imatrix](https://huggingface.co/mradermacher/MS-Schisandra-22B-v0.2-i1-GGUF)
+
+exl2: [4.65bpw](https://huggingface.co/waldie/MS-Schisandra-22B-v0.2-4.65bpw-h6-exl2) [5.5bpw](https://huggingface.co/waldie/MS-Schisandra-22B-v0.2-5.5bpw-h6-exl2) [6.5bpw](https://huggingface.co/waldie/MS-Schisandra-22B-v0.2-6.5bpw-h6-exl2)
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+***
+
+### Settings
+
+Prompt format: Mistral-V3 or (this)[https://huggingface.co/ToastyPigeon/ST-Presets-Mistral-Small/resolve/main/ST-formatting-Mistral-Small-Oneshot.json]
+
+Samplers: [These](https://qu.ax/BCRKS.json) or [These](https://qu.ax/OusTx.json)
+
+***
 
 ## Merge Details
-### Merge Method
+### Merging steps
 
-This model was merged using the della_linear merge method using SchisandraVA2 as a base.
+## Step1 
+(Config partially taken from (here)[https://huggingface.co/Casual-Autopsy/L3-Super-Nova-RP-8B])
 
-### Models Merged
+```yaml
+base_model: spow12/ChatWaifu_v2.0_22B
+parameters:
+  int8_mask: true
+  rescale: true
+  normalize: false
+dtype: bfloat16
+tokenizer_source: base
+merge_method: della
+models:
+  - model: Envoid/Mistral-Small-NovusKyver
+    parameters:
+      density: [0.35, 0.65, 0.5, 0.65, 0.35]
+      epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
+      lambda: 0.85
+      weight: [-0.01891, 0.01554, -0.01325, 0.01791, -0.01458]
+  - model: rAIfle/Acolyte-22B
+    parameters:
+      density: [0.6, 0.4, 0.5, 0.4, 0.6]
+      epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
+      lambda: 0.85
+      weight: [0.01847, -0.01468, 0.01503, -0.01822, 0.01459]
+```
+
+## Step2
+(Config partially taken from (here)[https://huggingface.co/Casual-Autopsy/L3-Super-Nova-RP-8B])
+
+```yaml
+base_model: InferenceIllusionist/SorcererLM-22B
+parameters:
+  int8_mask: true
+  rescale: true
+  normalize: false
+dtype: bfloat16
+tokenizer_source: base
+merge_method: della
+models:
+  - model: crestf411/MS-sunfall-v0.7.0
+    parameters:
+      density: [0.35, 0.65, 0.5, 0.65, 0.35]
+      epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
+      lambda: 0.85
+      weight: [-0.01891, 0.01554, -0.01325, 0.01791, -0.01458]
+  - model: anthracite-org/magnum-v4-22b
+    parameters:
+      density: [0.6, 0.4, 0.5, 0.4, 0.6]
+      epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
+      lambda: 0.85
+      weight: [0.01847, -0.01468, 0.01503, -0.01822, 0.01459]
+```
 
-The following models were included in the merge:
-* [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409)
+## SchisandraVA2
+(Config taken from (here)[https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff-4.0])
 
-### Configuration
+```yaml
+merge_method: della_linear
+dtype: bfloat16
+parameters:
+  normalize: true
+  int8_mask: true
+tokenizer_source: base
+base_model: TheDrummer/UnslopSmall-22B-v1
+models:
+    - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: Step1
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: allura-org/MS-Meadowlark-22B
+      parameters:
+        density: 0.55
+        weight: 1
+    - model: Step2
+      parameters:
+        density: 0.55
+        weight: 1
+```
 
-The following YAML configuration was used to produce this model:
+## Schisandra-v0.2
 
 ```yaml
 dtype: bfloat16
@@ -61,4 +182,4 @@ models:
         - filter: down_proj
           value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
         - value: 1
-```
+```