Adding Evaluation Results (#1)

- Adding Evaluation Results (b38d6355c9f4bbf69211346fe70dd52af96fe50f)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -3,16 +3,119 @@ language:
 - en
 - es
 - ca
+license: apache-2.0
 tags:
 - FLOR
 - bloom
 - spanish
 - catalan
 - english
-pipeline_tag: text-generation
-license: apache-2.0
 datasets:
 - teknium/OpenHermes-2.5
+pipeline_tag: text-generation
+model-index:
+- name: OpenHermes-2.5-FLOR-6.3B
+  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: 33.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
+      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: 54.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
+      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: 25.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
+      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: 46.12
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
+      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: 62.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
+      name: Open LLM Leaderboard
 ---
 
 # OpenHermes-2.5-FLOR-6.3B 
@@ -23,4 +126,17 @@ La millor manera d'usar **OpenHermes-2.5-FLOR-6.3B** és amb el format **ChatML*
 
 ## Quantitzats
 
-Podeu trobar el model quantitzat i en format GGUF a [OpenHermes-2.5-FLOR-6.3B-GGUF](xaviviro/OpenHermes-2.5-FLOR-6.3B-GGUF)
+Podeu trobar el model quantitzat i en format GGUF a [OpenHermes-2.5-FLOR-6.3B-GGUF](xaviviro/OpenHermes-2.5-FLOR-6.3B-GGUF)
+# [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_xaviviro__OpenHermes-2.5-FLOR-6.3B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.04|
+|AI2 Reasoning Challenge (25-Shot)|33.45|
+|HellaSwag (10-Shot)              |54.53|
+|MMLU (5-Shot)                    |25.18|
+|TruthfulQA (0-shot)              |46.12|
+|Winogrande (5-shot)              |62.98|
+|GSM8k (5-shot)                   | 0.00|
+