Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- NousResearch/Hermes-3-Llama-3.2-3B
-- lunahr/Hermes-3-Llama-3.2-3B-abliterated
-- lunahr/thea-rp-3b-25r
+license: llama3.2
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3.2
+base_model:
+- NousResearch/Hermes-3-Llama-3.2-3B
+- lunahr/Hermes-3-Llama-3.2-3B-abliterated
+- lunahr/thea-rp-3b-25r
+model-index:
+- name: Llama_3.2_3b_Kermes_v1
+  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: 48.52
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
+      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: 21.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
+      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: 3.1
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
+      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: 3.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
+      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: 9.31
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
+      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: 17.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -40,4 +135,17 @@ models:
 base_model: NousResearch/Hermes-3-Llama-3.2-3B
 dtype: float16
 normalize: true
-```
+```
+# [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/Nexesenex__Llama_3.2_3b_Kermes_v1-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.07|
+|IFEval (0-Shot)    |48.52|
+|BBH (3-Shot)       |21.17|
+|MATH Lvl 5 (4-Shot)| 3.10|
+|GPQA (0-shot)      | 3.13|
+|MuSR (0-shot)      | 9.31|
+|MMLU-PRO (5-shot)  |17.19|
+