Create README.md

README.md

@@ -0,0 +1,179 @@
+---
+base_model:
+- arcee-ai/Llama-3.1-SuperNova-Lite
+- unsloth/Llama-3.1-Storm-8B
+- unsloth/Meta-Llama-3.1-8B-Instruct
+- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+library_name: transformers
+tags:
+- mergekit
+- merge
+model-index:
+- name: ZEUS-8B-V13
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 79.04
+      name: averaged accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V13
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 32.73
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V13
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 20.62
+      name: exact match
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V13
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.84
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V13
+      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: 8.39
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V13
+      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: 32.35
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V13
+      name: Open LLM Leaderboard
+license: llama3.1
+---
+# ZEUS 8B 🌩️ V13
+
+👍
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
+* [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B)
+* [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: unsloth/Meta-Llama-3.1-8B-Instruct
+dtype: bfloat16
+merge_method: dare_ties
+parameters:
+  int8_mask: 1.0
+  normalize: 1.0
+  random_seed: 145.0
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model: unsloth/Llama-3.1-Storm-8B
+    parameters:
+      density: 0.95
+      weight: 0.33
+  - layer_range: [0, 32]
+    model: arcee-ai/Llama-3.1-SuperNova-Lite
+    parameters:
+      density: 0.9
+      weight: 0.29
+  - layer_range: [0, 32]
+    model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+    parameters:
+      density: 0.92
+      weight: 0.38
+  - layer_range: [0, 32]
+    model: unsloth/Meta-Llama-3.1-8B-Instruct
+tokenizer_source: union
+```
+# [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/T145__ZEUS-8B-V13-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=T145%2FZEUS-8B-V13&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    30.50|
+|IFEval (0-Shot)    |    79.04|
+|BBH (3-Shot)       |    32.73|
+|MATH Lvl 5 (4-Shot)|    20.62|
+|GPQA (0-shot)      |     9.84|
+|MuSR (0-shot)      |     8.39|
+|MMLU-PRO (5-shot)  |    32.35|