Update README.md

README.md

@@ -1,179 +1,186 @@
----
-base_model:
-- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
-- unsloth/Meta-Llama-3.1-8B-Instruct
-- unsloth/Llama-3.1-Storm-8B
-- arcee-ai/Llama-3.1-SuperNova-Lite
-- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
-library_name: transformers
-tags:
-- mergekit
-- merge
-model-index:
-- name: ZEUS-8B-V22
-  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: 79.95
-      name: averaged accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
-      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: 32.21
-      name: normalized accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
-      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: 20.24
-      name: exact match
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
-      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: 10.4
-      name: acc_norm
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
-      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: 9.37
-      name: acc_norm
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
-      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: 32.64
-      name: accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
-      name: Open LLM Leaderboard
----
-# Untitled Model (1)
-
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-
-## 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:
-* [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
-* [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B)
-* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
-* [VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct)
-
-### 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: 0.94
-      weight: 0.35
-  - layer_range: [0, 32]
-    model: arcee-ai/Llama-3.1-SuperNova-Lite
-    parameters:
-      density: 0.92
-      weight: 0.26
-  - layer_range: [0, 32]
-    model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
-    parameters:
-      density: 0.91
-      weight: 0.2
-  - layer_range: [0, 32]
-    model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
-    parameters:
-      density: 0.93
-      weight: 0.19
-  - layer_range: [0, 32]
-    model: unsloth/Meta-Llama-3.1-8B-Instruct
-tokenizer:
-  tokens:
-    <|begin_of_text|>:
-      force: true
-      source: unsloth/Meta-Llama-3.1-8B-Instruct
-    <|eot_id|>:
-      force: true
-      source: unsloth/Meta-Llama-3.1-8B-Instruct
-    <|finetune_right_pad_id|>:
-      force: true
-      source: unsloth/Meta-Llama-3.1-8B-Instruct
-```
+---
+base_model:
+- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+- unsloth/Meta-Llama-3.1-8B-Instruct
+- unsloth/Llama-3.1-Storm-8B
+- arcee-ai/Llama-3.1-SuperNova-Lite
+- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
+library_name: transformers
+tags:
+- mergekit
+- merge
+model-index:
+- name: ZEUS-8B-V22
+  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: 79.95
+      name: averaged accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
+      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: 32.21
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
+      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: 20.24
+      name: exact match
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
+      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: 10.4
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
+      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: 9.37
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
+      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: 32.64
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V22
+      name: Open LLM Leaderboard
+license: llama3.1
+---
+# ZEUS 8B 🌩️ V22
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## 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:
+* [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)
+* [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B)
+* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
+* [VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct)
+
+### 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: 0.94
+      weight: 0.35
+  - layer_range: [0, 32]
+    model: arcee-ai/Llama-3.1-SuperNova-Lite
+    parameters:
+      density: 0.92
+      weight: 0.26
+  - layer_range: [0, 32]
+    model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
+    parameters:
+      density: 0.91
+      weight: 0.2
+  - layer_range: [0, 32]
+    model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+    parameters:
+      density: 0.93
+      weight: 0.19
+  - layer_range: [0, 32]
+    model: unsloth/Meta-Llama-3.1-8B-Instruct
+tokenizer:
+  tokens:
+    <|begin_of_text|>:
+      force: true
+      source: unsloth/Meta-Llama-3.1-8B-Instruct
+    <|eot_id|>:
+      force: true
+      source: unsloth/Meta-Llama-3.1-8B-Instruct
+    <|finetune_right_pad_id|>:
+      force: true
+      source: unsloth/Meta-Llama-3.1-8B-Instruct
+```
 
 # [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-V22-details)!
@@ -187,5 +194,4 @@ Summarized results can be found [here](https://huggingface.co/datasets/open-llm-
 |MATH Lvl 5 (4-Shot)|    20.24|
 |GPQA (0-shot)      |    10.40|
 |MuSR (0-shot)      |     9.37|
-|MMLU-PRO (5-shot)  |    32.64|
-
+|MMLU-PRO (5-shot)  |    32.64|