Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
+language:
+- en
+license: apache-2.0
+tags:
+- mergekit
+- merge
 base_model:
 - flemmingmiguel/MBX-7B-v3
 - paulml/NeuralOmniWestBeaglake-7B
 - FelixChao/Faraday-7B
 - paulml/NeuralOmniBeagleMBX-v3-7B
-tags:
-- mergekit
-- merge
-license: apache-2.0
-language:
-- en
+model-index:
+- name: Samlagast-7B-bf16
+  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: 73.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
+      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: 89.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
+      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: 64.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
+      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: 73.9
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
+      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: 85.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
+      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: 67.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/eDLmpTkM4vuk8HiQcUzWv.png)
@@ -58,4 +161,17 @@ parameters:
   int8_mask: true
 dtype: float16
 
-```
+```
+# [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_Kquant03__Samlagast-7B-bf16)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.81|
+|AI2 Reasoning Challenge (25-Shot)|73.98|
+|HellaSwag (10-Shot)              |89.34|
+|MMLU (5-Shot)                    |64.58|
+|TruthfulQA (0-shot)              |73.90|
+|Winogrande (5-shot)              |85.48|
+|GSM8k (5-shot)                   |67.55|
+