Adding Evaluation Results

README.md

@@ -1,5 +1,16 @@
 ---
+language:
+- en
 license: llama2
+tags:
+- code
+- text-generation-inference
+- Information Extraction
+- IE
+- Named Entity Recogniton
+- Event Extraction
+- Relation Extraction
+- LLaMA
 datasets:
 - ACE05
 - bc5cdr
@@ -9,20 +20,112 @@ datasets:
 - rams
 - tacred
 - wnut_17
-language:
-- en
 metrics:
 - f1
 pipeline_tag: text-generation
-tags:
-- code
-- text-generation-inference
-- Information Extraction
-- IE
-- Named Entity Recogniton
-- Event Extraction
-- Relation Extraction
-- LLaMA
+model-index:
+- name: GoLLIE-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: 36.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HiTZ/GoLLIE-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: 57.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HiTZ/GoLLIE-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: 29.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HiTZ/GoLLIE-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: 39.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HiTZ/GoLLIE-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: 58.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HiTZ/GoLLIE-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: 3.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HiTZ/GoLLIE-7B
+      name: Open LLM Leaderboard
 ---
 
 <p align="center">
@@ -178,4 +281,17 @@ For more info, read our [📖Paper](https://arxiv.org/abs/2310.03668).
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```
+```
+# [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_HiTZ__GoLLIE-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.48|
+|AI2 Reasoning Challenge (25-Shot)|36.09|
+|HellaSwag (10-Shot)              |57.93|
+|MMLU (5-Shot)                    |29.38|
+|TruthfulQA (0-shot)              |39.27|
+|Winogrande (5-shot)              |58.96|
+|GSM8k (5-shot)                   | 3.26|
+