Adding Evaluation Results

README.md

@@ -2,6 +2,8 @@
 language:
 - en
 license: llama2
+tags:
+- legal
 datasets:
 - EleutherAI/pile
 - Open-Orca/OpenOrca
@@ -10,8 +12,109 @@ datasets:
 metrics:
 - accuracy
 pipeline_tag: text-generation
-tags:
-- legal
+model-index:
+- name: law-chat
+  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: 53.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/law-chat
+      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: 76.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/law-chat
+      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: 50.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/law-chat
+      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: 43.53
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/law-chat
+      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: 75.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/law-chat
+      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: 18.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AdaptLLM/law-chat
+      name: Open LLM Leaderboard
 ---
 
 # Domain Adaptation of Large Language Models
@@ -90,4 +193,17 @@ If you find our work helpful, please cite us:
   journal={arXiv preprint arXiv:2309.09530},
   year={2023}
 }
-```
+```
+# [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_AdaptLLM__law-chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.88|
+|AI2 Reasoning Challenge (25-Shot)|53.41|
+|HellaSwag (10-Shot)              |76.16|
+|MMLU (5-Shot)                    |50.24|
+|TruthfulQA (0-shot)              |43.53|
+|Winogrande (5-shot)              |75.45|
+|GSM8k (5-shot)                   |18.50|
+