Adding Evaluation Results (#1)

- Adding Evaluation Results (c1065fcdc9337c919a0da354eb432b8c0ac1bd44)


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

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- rhysjones/phi-2-orange-v2
-- Weyaxi/Einstein-v4-phi2
+license: mit
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: mit
+base_model:
+- rhysjones/phi-2-orange-v2
+- Weyaxi/Einstein-v4-phi2
+model-index:
+- name: L-MChat-Small
+  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: 61.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 75.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 57.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 49.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 74.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      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: 58.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Artples/L-MChat-Small
+      name: Open LLM Leaderboard
 ---
 <div style="text-align:center;width:250px;height:250px;">
     <img src="https://cdn.lauche.eu/L-MChat-Series-Logo.jpeg" alt="L-MChat-Series-Logo"">
@@ -65,4 +168,17 @@ dtype: bfloat16
 
 ## Usage
 
-Use it with the ChatML format, you can also use the Inference-API for this Model.
+Use it with the ChatML format, you can also use the Inference-API for this Model.
+# [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_Artples__L-MChat-Small)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.14|
+|AI2 Reasoning Challenge (25-Shot)|61.60|
+|HellaSwag (10-Shot)              |75.90|
+|MMLU (5-Shot)                    |57.41|
+|TruthfulQA (0-shot)              |49.94|
+|Winogrande (5-shot)              |74.98|
+|GSM8k (5-shot)                   |58.98|
+