Adding Evaluation Results

README.md

@@ -1,10 +1,112 @@
 ---
 license: cc-by-nc-4.0
-
-base_model: [mistralai/Mixtral-8x7B-Instruct-v0.1]
-
 tags:
 - dpo
+base_model:
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+model-index:
+- name: raccoon-small
+  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: 74.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/raccoon-small
+      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: 88.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/raccoon-small
+      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: 64.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/raccoon-small
+      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: 76.74
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/raccoon-small
+      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: 87.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/raccoon-small
+      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: 56.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/raccoon-small
+      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.
@@ -12,4 +114,17 @@ tags:
 The merged model has 19 billion parraraameters and was made trained on 640GB of vram cluster
 
 ## Merge me baby one more time
-### Sending this contraption out straight to mergeland, would be hilarious if it gets 1st
+### Sending this contraption out straight to mergeland, would be hilarious if it gets 1st
+# [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__raccoon-small)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.78|
+|AI2 Reasoning Challenge (25-Shot)|74.40|
+|HellaSwag (10-Shot)              |88.73|
+|MMLU (5-Shot)                    |64.55|
+|TruthfulQA (0-shot)              |76.74|
+|Winogrande (5-shot)              |87.37|
+|GSM8k (5-shot)                   |56.86|
+