Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ms-schisandra-22b-v0.2.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,292 @@
+---
+language:
+- en
+license: other
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- unsloth/Mistral-Small-Instruct-2409
+- 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
+model-index:
+- name: MS-Schisandra-22B-v0.2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 63.83
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 40.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 19.94
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.41
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 10.67
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 34.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nohobby/MS-Schisandra-22B-v0.2
+      name: Open LLM Leaderboard
+---
+***
+## 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
+
+Prompt format: Mistral-V3
+
+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)
+
+***
+
+### Settings
+
+My SillyTavern preset: https://huggingface.co/Nohobby/MS-Schisandra-22B-v0.2/resolve/main/ST-formatting-Schisandra.json
+
+***
+
+## Merge Details
+### Merging steps
+
+## Step1 
+(Config partially taken from [here](https://huggingface.co/Casual-Autopsy/L3-Super-Nova-RP-8B))
+
+```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]
+```
+
+## SchisandraVA2
+(Config taken from [here](https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff-4.0))
+
+```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
+```
+
+## Schisandra-v0.2
+
+```yaml
+dtype: bfloat16
+tokenizer_source: base
+merge_method: della_linear
+parameters:
+  density: 0.5
+base_model: SchisandraVA2
+models:
+  - model: unsloth/Mistral-Small-Instruct-2409
+    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: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
+        - value: 0
+  - model: SchisandraVA2
+    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: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
+        - value: 1
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Nohobby__MS-Schisandra-22B-v0.2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |30.22|
+|IFEval (0-Shot)    |63.83|
+|BBH (3-Shot)       |40.61|
+|MATH Lvl 5 (4-Shot)|19.94|
+|GPQA (0-shot)      |11.41|
+|MuSR (0-shot)      |10.67|
+|MMLU-PRO (5-shot)  |34.85|
+

ms-schisandra-22b-v0.2.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3900c77335a1aed8a88a678d5fa24bdfc3cee2064e9f28bccb4abd9fd38f21
+size 12569164736