Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-base_model:
-- jondurbin/bagel-dpo-34b-v0.2
-- one-man-army/UNA-34Beagles-32K-bf16-v1
+license: mit
 tags:
 - mergekit
 - merge
-license: mit
+base_model:
+- jondurbin/bagel-dpo-34b-v0.2
+- one-man-army/UNA-34Beagles-32K-bf16-v1
+model-index:
+- name: Yi-34b-x2
+  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: 72.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sumo43/Yi-34b-x2
+      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: 85.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sumo43/Yi-34b-x2
+      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: 76.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sumo43/Yi-34b-x2
+      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: 72.1
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sumo43/Yi-34b-x2
+      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: 82.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sumo43/Yi-34b-x2
+      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: 60.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sumo43/Yi-34b-x2
+      name: Open LLM Leaderboard
 ---
 # merged
 
@@ -43,4 +146,17 @@ slices:
     model: jondurbin/bagel-dpo-34b-v0.2
   - layer_range: [0, 60]
     model: one-man-army/UNA-34Beagles-32K-bf16-v1
-```
+```
+# [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_sumo43__Yi-34b-x2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.02|
+|AI2 Reasoning Challenge (25-Shot)|72.87|
+|HellaSwag (10-Shot)              |85.70|
+|MMLU (5-Shot)                    |76.64|
+|TruthfulQA (0-shot)              |72.10|
+|Winogrande (5-shot)              |82.79|
+|GSM8k (5-shot)                   |60.05|
+