Adding Evaluation Results

README.md

@@ -1,4 +1,14 @@
 ---
+language:
+- en
+- de
+license: llama2
+library_name: transformers
+tags:
+- goliath
+- deutsch
+- llama2
+- discoresearch
 datasets:
 - Open-Orca/SlimOrca-Dedup
 - teknium/openhermes
@@ -10,19 +20,112 @@ datasets:
 - LeoLM/OpenSchnabeltier
 - bjoernp/ultrachat_de
 - LDJnr/Capybara
-language:
-- en
-- de
-library_name: transformers
 pipeline_tag: text-generation
-license: llama2
 model_creator: DiscoResearch
 model_type: llama
-tags:
-- goliath
-- deutsch
-- llama2
-- discoresearch
+model-index:
+- name: DiscoLM-70b
+  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: 68.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DiscoResearch/DiscoLM-70b
+      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: 86.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DiscoResearch/DiscoLM-70b
+      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: 68.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DiscoResearch/DiscoLM-70b
+      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: 57.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DiscoResearch/DiscoLM-70b
+      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: 83.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DiscoResearch/DiscoLM-70b
+      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: 63.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=DiscoResearch/DiscoLM-70b
+      name: Open LLM Leaderboard
 ---
 
 
@@ -183,4 +286,17 @@ We are standing on the shoulders of giants; many thanks in no particular order t
 ## Disclaimer
 
 The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.
-This model should only be used for research purposes. The original Llama2 license and all restrictions of datasets used to train this model apply.
+This model should only be used for research purposes. The original Llama2 license and all restrictions of datasets used to train this model apply.
+# [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_DiscoResearch__DiscoLM-70b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.37|
+|AI2 Reasoning Challenge (25-Shot)|68.77|
+|HellaSwag (10-Shot)              |86.10|
+|MMLU (5-Shot)                    |68.58|
+|TruthfulQA (0-shot)              |57.64|
+|Winogrande (5-shot)              |83.58|
+|GSM8k (5-shot)                   |63.53|
+