Adding Evaluation Results (#1)

- Adding Evaluation Results (1bf608fd506f2e3bd49522b59d5b31d173d2c626)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,4 +1,7 @@
 ---
+tags:
+- mergekit
+- merge
 base_model:
 - teknium/OpenHermes-2.5-Mistral-7B
 - nlpguy/Hermes-low-tune-2
@@ -6,11 +9,111 @@ base_model:
 - openaccess-ai-collective/openhermes-2_5-dpo-no-robots
 - flemmingmiguel/Mistrality-7B
 - beowolx/MistralHermes-CodePro-7B-v1
-tags:
-- mergekit
-- merge
 license_name: apache-2.0-mit-dual-license
 license_link: https://huggingface.co/nlpguy/Hermes-low-tune-3.1/raw/main/LICENSE
+model-index:
+- name: Hermes-low-tune-3.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 65.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 84.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 53.59
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 78.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
+      name: Open LLM Leaderboard
 ---
 # merged
 
@@ -62,4 +165,17 @@ slices:
     model: openaccess-ai-collective/openhermes-2_5-dpo-no-robots
     parameters:
       weight: 0.2
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nlpguy__Hermes-low-tune-3.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.31|
+|AI2 Reasoning Challenge (25-Shot)|65.44|
+|HellaSwag (10-Shot)              |84.60|
+|MMLU (5-Shot)                    |64.13|
+|TruthfulQA (0-shot)              |53.59|
+|Winogrande (5-shot)              |78.61|
+|GSM8k (5-shot)                   |63.46|
+