Adding Evaluation Results (#1)

- Adding Evaluation Results (3b4851b576a49a8008def1cca3392b7bee07267a)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,13 +1,116 @@
 ---
-base_model:
-- Dampfinchen/Llama-3-8B-Ultra-Instruct
-- NousResearch/Meta-Llama-3-8B
-- NousResearch/Meta-Llama-3-8B-Instruct
+license: llama3
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: llama3
+base_model:
+- Dampfinchen/Llama-3-8B-Ultra-Instruct
+- NousResearch/Meta-Llama-3-8B
+- NousResearch/Meta-Llama-3-8B-Instruct
+model-index:
+- name: Llama-3-8B-Ultra-Instruct-SaltSprinkle
+  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: 61.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle
+      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: 77.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle
+      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: 67.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle
+      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: 52.82
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle
+      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: 74.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle
+      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: 70.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -44,4 +147,17 @@ base_model: NousResearch/Meta-Llama-3-8B
 dtype: bfloat16
 ```
 
-Test of salt sprinkle methode. The goal is to retain all of L3 Instruct's capabilities while adding better RP, RAG, German and story writing capabilities in the form of Ultra Instruct. Model may generate harmful responses, I'm not responsible for what you do with this model. 
+Test of salt sprinkle methode. The goal is to retain all of L3 Instruct's capabilities while adding better RP, RAG, German and story writing capabilities in the form of Ultra Instruct. Model may generate harmful responses, I'm not responsible for what you do with this model. 
+# [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_Dampfinchen__Llama-3-8B-Ultra-Instruct-SaltSprinkle)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.61|
+|AI2 Reasoning Challenge (25-Shot)|61.35|
+|HellaSwag (10-Shot)              |77.76|
+|MMLU (5-Shot)                    |67.88|
+|TruthfulQA (0-shot)              |52.82|
+|Winogrande (5-shot)              |74.98|
+|GSM8k (5-shot)                   |70.89|
+