Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-datasets:
-- HuggingFaceH4/ultrachat_200k
 language:
 - en
 license: other
+datasets:
+- HuggingFaceH4/ultrachat_200k
 base_model: Qwen/Qwen-7B
+model-index:
+- name: UltraQwen-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: 51.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/UltraQwen-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: 77.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/UltraQwen-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: 59.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/UltraQwen-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: 48.2
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/UltraQwen-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: 73.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/UltraQwen-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: 44.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/UltraQwen-7B
+      name: Open LLM Leaderboard
 ---
 # Model description
 The model was trained on about 100,000 examples of the HuggingFaceH4/ultrachat_200k dataset, with plans to release more checkpoints later on.
@@ -20,4 +123,17 @@ temperature=0.2, top_p=0.14, top_k=12, repetition_penalty=1.1
 
 # License
 
-Please make sure to read the Qwen licensing agreement before using this model.
+Please make sure to read the Qwen licensing agreement before using this model.
+# [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_Locutusque__UltraQwen-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.17|
+|AI2 Reasoning Challenge (25-Shot)|51.71|
+|HellaSwag (10-Shot)              |77.93|
+|MMLU (5-Shot)                    |59.16|
+|TruthfulQA (0-shot)              |48.20|
+|Winogrande (5-shot)              |73.95|
+|GSM8k (5-shot)                   |44.05|
+