Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 inference: false
+model-index:
+- name: vicuna-13B-1.1-HF
+  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: 52.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/vicuna-13B-1.1-HF
+      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: 80.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/vicuna-13B-1.1-HF
+      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: 51.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/vicuna-13B-1.1-HF
+      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: 52.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/vicuna-13B-1.1-HF
+      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: 74.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/vicuna-13B-1.1-HF
+      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: 8.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/vicuna-13B-1.1-HF
+      name: Open LLM Leaderboard
 ---
 
 **NOTE: New version available**  
@@ -50,4 +153,17 @@ See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/doc
 
 ## Acknowledgement
 
-Special thanks to [@TheBloke](https://huggingface.co/TheBloke) for hosting this merged version of weights earlier.
+Special thanks to [@TheBloke](https://huggingface.co/TheBloke) for hosting this merged version of weights earlier.
+# [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_TheBloke__vicuna-13B-1.1-HF)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |53.29|
+|AI2 Reasoning Challenge (25-Shot)|52.73|
+|HellaSwag (10-Shot)              |80.13|
+|MMLU (5-Shot)                    |51.94|
+|TruthfulQA (0-shot)              |52.08|
+|Winogrande (5-shot)              |74.19|
+|GSM8k (5-shot)                   | 8.64|
+