Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
 license: cc-by-nc-nd-4.0
-base_model:
-- mistralai/Mixtral-8x7B-Instruct-v0.1
 tags:
 - dpo
 - merge
 - mergekit
+base_model:
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+model-index:
+- name: rizla-17
+  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: 73.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
+      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: 89.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
+      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: 64.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
+      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: 76.93
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
+      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: 87.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
+      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: 61.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
+      name: Open LLM Leaderboard
 ---
 # rizla been cooking while singing
 # This is an experimental model that I made by merging two 2expmixtrals The mergekitty is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.
@@ -13,4 +116,17 @@ tags:
 The merged model has 17 billion parraraameters and was made to run on 8gb of ram minimum in q3KL gguf.
 
 ## Merge me baby one more time
-### Sending this contraption out straight to mergeland, wwhheeeeeeeeeeeee LFG 🚀
+### Sending this contraption out straight to mergeland, wwhheeeeeeeeeeeee LFG 🚀
+# [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_rizla__rizla-17)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.67|
+|AI2 Reasoning Challenge (25-Shot)|73.63|
+|HellaSwag (10-Shot)              |89.72|
+|MMLU (5-Shot)                    |64.40|
+|TruthfulQA (0-shot)              |76.93|
+|Winogrande (5-shot)              |87.85|
+|GSM8k (5-shot)                   |61.49|
+