Adding Evaluation Results

README.md

@@ -5,16 +5,119 @@ language:
 - 'no'
 - da
 license: mit
-models:
-  - timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
 tags:
 - pretrained
 - flashback
 - web
 - conversational
+models:
+- timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
 pipeline_tag: text-generation
 widget:
 - text: Jag tycker att det är roligt med
+model-index:
+- name: Mistral-7B-v0.1-flashback-v2
+  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: 57.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      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: 80.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      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: 59.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      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: 40.66
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      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=timpal0l/Mistral-7B-v0.1-flashback-v2
+      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: 29.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
 ---
 
 # 🐈‍⬛ Mistral-7B-v0.1-flashback-v2
@@ -180,4 +283,17 @@ Tack och lov för apparna som jag kunde leda oss efter. Att åka kollektivt hade
 
 Tack ska ni ha för tipsen, igen. Tack till Stockholm för att ni tog emot oss med respekt han var så nöjd med resan.
 Hej så länge, vi kommer åter i framtiden! 😁
-```
+```
+# [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_timpal0l__Mistral-7B-v0.1-flashback-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.53|
+|AI2 Reasoning Challenge (25-Shot)|57.17|
+|HellaSwag (10-Shot)              |80.74|
+|MMLU (5-Shot)                    |59.98|
+|TruthfulQA (0-shot)              |40.66|
+|Winogrande (5-shot)              |77.19|
+|GSM8k (5-shot)                   |29.42|
+