Adding Evaluation Results (#1)

- Adding Evaluation Results (27a5b4f03a159a3689b5ddca5432eaa4e1ca575c)


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

README.md

@@ -1,14 +1,117 @@
 ---
-library_name: peft
-base_model: mistralai/Mistral-7B-v0.1
+language:
+- en
 license: mit
+library_name: peft
 datasets:
 - AtlasUnified/atlas-storyteller
-language:
-- en
 metrics:
 - perplexity
+base_model: mistralai/Mistral-7B-v0.1
 pipeline_tag: text-generation
+model-index:
+- name: Mistral-7B-LoreWeaver
+  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: 59.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
+      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: 83.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
+      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: 64.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
+      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: 42.15
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
+      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: 78.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
+      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: 37.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -225,4 +328,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Framework versions
 
-- PEFT 0.7.1
+- PEFT 0.7.1
+# [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_Reverb__Mistral-7B-LoreWeaver)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.93|
+|AI2 Reasoning Challenge (25-Shot)|59.98|
+|HellaSwag (10-Shot)              |83.29|
+|MMLU (5-Shot)                    |64.12|
+|TruthfulQA (0-shot)              |42.15|
+|Winogrande (5-shot)              |78.37|
+|GSM8k (5-shot)                   |37.68|
+