Adding Evaluation Results

README.md

@@ -1,11 +1,12 @@
 ---
+language:
+- de
+- en
+license: cc-by-nc-4.0
 tags:
 - merge
 - mergekit
 - lazymergekit
-language:
-- de
-- en
 base_model:
 - abideen/AlphaMonarch-dora
 - mayflowergmbh/Wiedervereinigung-7b-dpo
@@ -21,7 +22,109 @@ base_model:
 - malteos/hermeo-7b
 - FelixChao/WestSeverus-7B-DPO-v2
 - cognitivecomputations/openchat-3.5-0106-laser
-license: cc-by-nc-4.0
+model-index:
+- name: Spaetzle-v69-7b
+  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: 69.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
+      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: 86.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
+      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: 64.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
+      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: 65.61
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
+      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: 81.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
+      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: 68.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cstr/Spaetzle-v69-7b
+      name: Open LLM Leaderboard
 ---
 
 # Spaetzle-v69-7b
@@ -184,4 +287,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_cstr__Spaetzle-v69-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.87|
+|AI2 Reasoning Challenge (25-Shot)|69.54|
+|HellaSwag (10-Shot)              |86.77|
+|MMLU (5-Shot)                    |64.63|
+|TruthfulQA (0-shot)              |65.61|
+|Winogrande (5-shot)              |81.93|
+|GSM8k (5-shot)                   |68.76|
+