Adding Evaluation Results

README.md

@@ -1,14 +1,14 @@
 ---
-license: apache-2.0
 language:
 - en
 - code
-datasets:
-- open-phi/programming_books_llama
-- open-phi/textbooks
+license: apache-2.0
 tags:
 - merge
 - computer science
+datasets:
+- open-phi/programming_books_llama
+- open-phi/textbooks
 inference:
   parameters:
     do_sample: true
@@ -18,7 +18,110 @@ inference:
     max_new_tokens: 250
     repetition_penalty: 1.15
 widget:
-  - text: "To calculate the factorial of n, we can use the following function:"
+- text: 'To calculate the factorial of n, we can use the following function:'
+model-index:
+- name: TinyMistral-248M-v2.5
+  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: 24.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
+      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: 27.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
+      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: 23.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
+      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: 46.72
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
+      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: 47.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
+      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=Locutusque/TinyMistral-248M-v2.5
+      name: Open LLM Leaderboard
 ---
 # TinyMistral-248M-v2.5
 This model was created by merging TinyMistral-248M-v1 and v2, then further pretraining on synthetic textbooks. The resulting model's performance is superior to both, after personal evaluation.
@@ -52,4 +155,17 @@ This model can also answer basic questions, without needing to do any fine-tunin
 
 This model was also created as an attempt to fix the issue with V2 - the weights were prone to exploding gradients, making it difficult to fine-tune. This model is easier to fine-tune.
 
-To get the best out of this model, I recommend installing it, and trying it out yourself, as the model's performance seems to degrade in the inference API.
+To get the best out of this model, I recommend installing it, and trying it out yourself, as the model's performance seems to degrade in the inference API.
+# [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_Locutusque__TinyMistral-248M-v2.5)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |28.29|
+|AI2 Reasoning Challenge (25-Shot)|24.57|
+|HellaSwag (10-Shot)              |27.49|
+|MMLU (5-Shot)                    |23.15|
+|TruthfulQA (0-shot)              |46.72|
+|Winogrande (5-shot)              |47.83|
+|GSM8k (5-shot)                   | 0.00|
+