Adding Evaluation Results

README.md

@@ -1,7 +1,110 @@
 ---
+license: apache-2.0
 library_name: peft
 base_model: NeuralNovel/Tiger-7B-v0.1-LaserRMT-Math-5-10-15
-license: apache-2.0
+model-index:
+- name: Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+  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: 39.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NovoCode/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+      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: 82.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NovoCode/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+      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: 61.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NovoCode/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+      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: 48.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NovoCode/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+      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: 77.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NovoCode/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+      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: 35.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NovoCode/Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -202,4 +305,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Framework versions
 
-- PEFT 0.8.2
+- PEFT 0.8.2
+# [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_NovoCode__Tiger-7B-v0.1-LaserRMT-Math-5-10-15-Neural-DPO)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.36|
+|AI2 Reasoning Challenge (25-Shot)|39.42|
+|HellaSwag (10-Shot)              |82.58|
+|MMLU (5-Shot)                    |61.63|
+|TruthfulQA (0-shot)              |48.16|
+|Winogrande (5-shot)              |77.19|
+|GSM8k (5-shot)                   |35.18|
+