Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-inference: false
-license: llama2
 language:
 - en
+license: llama2
 tags:
 - information retrieval
 - reranker
+inference: false
+model-index:
+- name: rank_vicuna_7b_v1_fp16
+  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: 44.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=castorini/rank_vicuna_7b_v1_fp16
+      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: 65.67
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=castorini/rank_vicuna_7b_v1_fp16
+      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: 44.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=castorini/rank_vicuna_7b_v1_fp16
+      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: 45.13
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=castorini/rank_vicuna_7b_v1_fp16
+      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: 66.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=castorini/rank_vicuna_7b_v1_fp16
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=castorini/rank_vicuna_7b_v1_fp16
+      name: Open LLM Leaderboard
 ---
 
 # RankVicuna (FP16) Model Card
@@ -38,4 +141,17 @@ RankVicuna is finetuned from `lmsys/vicuna-7b-v1.5` with supervised instruction
 
 ## Evaluation
 
-RankVicuna is currently evaluated on DL19/DL20. See more details in our [paper](https://arxiv.org/pdf/2309.15088.pdf).
+RankVicuna is currently evaluated on DL19/DL20. See more details in our [paper](https://arxiv.org/pdf/2309.15088.pdf).
+# [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_castorini__rank_vicuna_7b_v1_fp16)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.36|
+|AI2 Reasoning Challenge (25-Shot)|44.62|
+|HellaSwag (10-Shot)              |65.67|
+|MMLU (5-Shot)                    |44.14|
+|TruthfulQA (0-shot)              |45.13|
+|Winogrande (5-shot)              |66.61|
+|GSM8k (5-shot)                   | 0.00|
+