Adding Evaluation Results (#1)

- Adding Evaluation Results (dffc10f4d74be9c182352aedee88bc640b4d297d)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,16 +1,119 @@
 ---
-library_name: peft
-base_model: mistralai/Mistral-7B-v0.1
-license: apache-2.0
-datasets:
-- upaya07/NeurIPS-LLM-data
 language:
 - en
+license: apache-2.0
+library_name: peft
 tags:
 - NeurIPS
 - NeurIPS LLM Efficiency Challenge
 - NeurIPS LLM Efficiency Challenge Winner Model
 - Team Upaya
+datasets:
+- upaya07/NeurIPS-LLM-data
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: Birbal-7B-V1
+  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: 62.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upaya07/Birbal-7B-V1
+      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: 84.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upaya07/Birbal-7B-V1
+      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: 63.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upaya07/Birbal-7B-V1
+      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: 45.46
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upaya07/Birbal-7B-V1
+      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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upaya07/Birbal-7B-V1
+      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: 41.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=upaya07/Birbal-7B-V1
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -202,4 +305,17 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.6.1
+- PEFT 0.6.1
+# [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_upaya07__Birbal-7B-V1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.82|
+|AI2 Reasoning Challenge (25-Shot)|62.88|
+|HellaSwag (10-Shot)              |84.88|
+|MMLU (5-Shot)                    |63.71|
+|TruthfulQA (0-shot)              |45.46|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |41.47|
+