Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,12 +1,115 @@
 ---
-library_name: peft
-base_model: Qwen/Qwen1.5-1.8B-Chat
-license: other
 language:
 - en
+license: other
+library_name: peft
 tags:
 - text-generation-inference
 - sft
+base_model: Qwen/Qwen1.5-1.8B-Chat
+model-index:
+- name: finetune_test_qwen15-1-8b-sft-lora
+  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: 36.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/finetune_test_qwen15-1-8b-sft-lora
+      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: 57.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/finetune_test_qwen15-1-8b-sft-lora
+      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: 44.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/finetune_test_qwen15-1-8b-sft-lora
+      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: 38.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/finetune_test_qwen15-1-8b-sft-lora
+      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: 61.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/finetune_test_qwen15-1-8b-sft-lora
+      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: 21.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/finetune_test_qwen15-1-8b-sft-lora
+      name: Open LLM Leaderboard
 ---
 
 Lora sft finetuned version of Qwen/Qwen1.5-1.8B-Chat
@@ -51,4 +154,17 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
 ### Framework versions
 
-- PEFT 0.8.2
+- PEFT 0.8.2
+# [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_eren23__finetune_test_qwen15-1-8b-sft-lora)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |43.27|
+|AI2 Reasoning Challenge (25-Shot)|36.18|
+|HellaSwag (10-Shot)              |57.77|
+|MMLU (5-Shot)                    |44.96|
+|TruthfulQA (0-shot)              |38.00|
+|Winogrande (5-shot)              |61.17|
+|GSM8k (5-shot)                   |21.53|
+