Adding Evaluation Results (#1)

- Adding Evaluation Results (b85a88e7038ef2c13c1313bd0a69f2790b415813)

README.md

@@ -1,4 +1,8 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
 tags:
 - rmdhirr/Foxglove_7B
 - ResplendentAI/Paradigm_Shift_7B
@@ -9,10 +13,109 @@ tags:
 base_model:
 - rmdhirr/Foxglove_7B
 - ResplendentAI/Paradigm_Shift_7B
-library_name: transformers
-license: apache-2.0
-language:
-- en
+model-index:
+- name: Anthesis_7B
+  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: 69.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rmdhirr/Anthesis_7B
+      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: 86.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rmdhirr/Anthesis_7B
+      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: 62.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rmdhirr/Anthesis_7B
+      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: 68.65
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rmdhirr/Anthesis_7B
+      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: 78.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rmdhirr/Anthesis_7B
+      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: 42.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rmdhirr/Anthesis_7B
+      name: Open LLM Leaderboard
 ---
 
 # 🌹 Anthesis_7B
@@ -35,4 +138,17 @@ base_model: ResplendentAI/Paradigm_Shift_7B
 parameters:
   int8_mask: true
 dtype: bfloat16
-```
+```
+# [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_rmdhirr__Anthesis_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.97|
+|AI2 Reasoning Challenge (25-Shot)|69.03|
+|HellaSwag (10-Shot)              |86.20|
+|MMLU (5-Shot)                    |62.06|
+|TruthfulQA (0-shot)              |68.65|
+|Winogrande (5-shot)              |78.93|
+|GSM8k (5-shot)                   |42.99|
+