Adding Evaluation Results (#2)

- Adding Evaluation Results (6b3f895b45251d34858adf27a5f0fe89336e53f5)


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

README.md

@@ -1,13 +1,116 @@
 ---
-license: cc-by-nc-sa-4.0
 language:
 - en
+license: cc-by-nc-sa-4.0
 library_name: transformers
 tags:
 - UNA
 - juanako
 - mixtral
 - MoE
+model-index:
+- name: UNAversal-8x7B-v1beta
+  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: 69.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNAversal-8x7B-v1beta
+      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: 86.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNAversal-8x7B-v1beta
+      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: 70.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNAversal-8x7B-v1beta
+      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: 71.97
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNAversal-8x7B-v1beta
+      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: 82.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNAversal-8x7B-v1beta
+      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: 61.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNAversal-8x7B-v1beta
+      name: Open LLM Leaderboard
 ---
 # UNAversal - Uniform Neural Alignment (MoE)
 
@@ -109,4 +212,17 @@ vllm (pretrained=fblgit/UNAversal-8x7B-v1beta,tensor_parallel_size=2,data_parall
 |Groups|Version|  Filter  |n-shot|  Metric   |Value |   |Stderr|
 |------|-------|----------|-----:|-----------|-----:|---|-----:|
 |bbh   |N/A    |get-answer|     0|exact_match|0.6752|±  |0.1772|
-```
+```
+# [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_fblgit__UNAversal-8x7B-v1beta)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.78|
+|AI2 Reasoning Challenge (25-Shot)|69.80|
+|HellaSwag (10-Shot)              |86.90|
+|MMLU (5-Shot)                    |70.39|
+|TruthfulQA (0-shot)              |71.97|
+|Winogrande (5-shot)              |82.00|
+|GSM8k (5-shot)                   |61.64|
+