Adding Evaluation Results (#2)

- Adding Evaluation Results (be9a29214c8cc2871201199b5089ebf14cf43ddd)


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

README.md

@@ -1,6 +1,109 @@
 ---
-library_name: transformers
 license: other
+library_name: transformers
+model-index:
+- name: Qwenchana-1.8B
+  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: 38.23
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/Qwenchana-1.8B
+      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: 59.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/Qwenchana-1.8B
+      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: 45.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/Qwenchana-1.8B
+      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: 39.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/Qwenchana-1.8B
+      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: 60.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/Qwenchana-1.8B
+      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: 19.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gmonsoon/Qwenchana-1.8B
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -196,4 +299,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+# [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_gmonsoon__Qwenchana-1.8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |43.83|
+|AI2 Reasoning Challenge (25-Shot)|38.23|
+|HellaSwag (10-Shot)              |59.92|
+|MMLU (5-Shot)                    |45.78|
+|TruthfulQA (0-shot)              |39.58|
+|Winogrande (5-shot)              |60.30|
+|GSM8k (5-shot)                   |19.18|
+