Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
-license: apache-2.0
 language:
 - fr
 - en
+license: apache-2.0
 tags:
 - code
 widget:
-- text: "<s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]"
+- text: <s> [|User|] Comment faire un bon plat ? </s>[|Assistant|]
+model-index:
+- name: MiniMerlin-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: 44.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=teilomillet/MiniMerlin-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: 66.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=teilomillet/MiniMerlin-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: 43.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=teilomillet/MiniMerlin-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: 47.07
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=teilomillet/MiniMerlin-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: 64.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=teilomillet/MiniMerlin-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: 20.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=teilomillet/MiniMerlin-3B
+      name: Open LLM Leaderboard
 ---
 SFT on a synthetic custom (french) dataset (2k), from general question answering, problem solving to code question.
 It's a POC.
@@ -33,4 +136,17 @@ inputs = tokenizer(text, return_tensors="pt").to(0)
 
 outputs = model.generate(**inputs, max_new_tokens=800)
 print(tokenizer.decode(outputs[0], skip_special_tokens=False))
-```
+```
+# [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_teilomillet__MiniMerlin-3B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.63|
+|AI2 Reasoning Challenge (25-Shot)|44.37|
+|HellaSwag (10-Shot)              |66.56|
+|MMLU (5-Shot)                    |43.21|
+|TruthfulQA (0-shot)              |47.07|
+|Winogrande (5-shot)              |64.40|
+|GSM8k (5-shot)                   |20.17|
+