Add evaluation results (LM Eval Harness, MT-Bench, AlpacaEval)

Note that MMLU is missing from https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json, so hasn't been included within the results

README.md

@@ -1,7 +1,4 @@
 ---
-model-index:
-- name: notus-7b-v1
-  results: []
 datasets:
 - argilla/ultrafeedback-binarized-preferences
 language:
@@ -15,6 +12,140 @@ tags:
 - preference
 - ultrafeedback
 license: mit
+model-index:
+- name: notus-7b-v1
+  results:
+  # AI2 Reasoning Challenge (25-Shot)
+  - 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
+         name: normalized accuracy
+         value: 0.6459044368600683
+    source:
+      name: Open LLM Leaderboard Results
+      url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
+  # HellaSwag (10-shot)
+  - 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
+         name: normalized accuracy
+         value: 0.8478390758812986
+    source:
+      name: Open LLM Leaderboard Results
+      url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
+  # DROP (3-shot)
+  - task: 
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Drop (3-Shot)
+      type: drop
+      split: validation
+      args:
+        num_few_shot: 3
+    metrics:
+       - type: f1
+         name: f1 score
+         value: 0.08913590604026835
+    source:
+      name: Open LLM Leaderboard Results
+      url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
+  # TruthfulQA (0-shot)
+  - 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: 0.5436768358952805
+    source:
+      name: Open LLM Leaderboard Results
+      url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
+  # GSM8k (5-shot)
+  - 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
+         name: accuracy
+         value: 0.1516300227445034
+    source:
+      name: Open LLM Leaderboard Results
+      url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
+  # Winogrande (5-shot)
+  - 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
+         name: accuracy
+         value: 0.7940015785319653
+    source:
+      name: Open LLM Leaderboard Results
+      url: https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
+  # AlpacaEval
+  - task: 
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AlpacaEval
+      type: tatsu-lab/alpaca_eval
+    metrics:
+       - type: tatsu-lab/alpaca_eval
+         name: win rate
+         value: 0.9142
+    source:
+      url: https://tatsu-lab.github.io/alpaca_eval/
+  # MT-Bench
+  - task: 
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MT-Bench
+      type: unknown
+    metrics:
+       - type: unknown
+         name: score
+         value: 7.30
+    source:
+      url: https://huggingface.co/spaces/lmsys/mt-bench
 ---
 
 <div align="center">