Adding Evaluation Results (#1)

- Adding Evaluation Results (66ea981268e371ed63684b9be41ef505c8cfeaf9)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,16 +1,119 @@
 ---
-license: mit
-base_model: teknium/OpenHermes-2.5-Mistral-7B
-datasets:
-- rxavier/economicus
 language:
 - en
+license: mit
 tags:
 - chatml
 - mistral
 - instruct
 - openhermes
 - economics
+datasets:
+- rxavier/economicus
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model-index:
+- name: Taurus-7B-1.0
+  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: 63.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      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: 83.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      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: 63.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      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: 50.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      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: 78.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      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: 59.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
+      name: Open LLM Leaderboard
 ---
 
 # Taurus 7B 1.0
@@ -70,4 +173,17 @@ print(tokenizer.decode(outputs["sequences"].cpu().tolist()[0]))
 
 ## GGUF quants
 
-You can find GGUF quants for llama.cpp [here](https://huggingface.co/rxavier/Taurus-7B-1.0-GGUF).
+You can find GGUF quants for llama.cpp [here](https://huggingface.co/rxavier/Taurus-7B-1.0-GGUF).
+# [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_rxavier__Taurus-7B-1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.40|
+|AI2 Reasoning Challenge (25-Shot)|63.57|
+|HellaSwag (10-Shot)              |83.64|
+|MMLU (5-Shot)                    |63.50|
+|TruthfulQA (0-shot)              |50.21|
+|Winogrande (5-shot)              |78.14|
+|GSM8k (5-shot)                   |59.36|
+