Adding Evaluation Results

README.md

@@ -3,6 +3,109 @@ license: apache-2.0
 datasets:
 - Open-Orca/SlimOrca
 pipeline_tag: text-generation
+model-index:
+- name: ThetaWave-7B-sft
+  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: 63.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Liangmingxin/ThetaWave-7B-sft
+      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: 84.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Liangmingxin/ThetaWave-7B-sft
+      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: 63.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Liangmingxin/ThetaWave-7B-sft
+      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: 59.74
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Liangmingxin/ThetaWave-7B-sft
+      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: 79.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Liangmingxin/ThetaWave-7B-sft
+      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: 56.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Liangmingxin/ThetaWave-7B-sft
+      name: Open LLM Leaderboard
 ---
 
 Obtained from freecs/ThetaWave-7B after SFT fine tuning.
@@ -64,4 +167,17 @@ model.to(device)
 generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
 decoded = tokenizer.batch_decode(generated_ids)
 print(decoded[0])
-```
+```
+# [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_Liangmingxin__ThetaWave-7B-sft)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.92|
+|AI2 Reasoning Challenge (25-Shot)|63.14|
+|HellaSwag (10-Shot)              |84.42|
+|MMLU (5-Shot)                    |63.78|
+|TruthfulQA (0-shot)              |59.74|
+|Winogrande (5-shot)              |79.64|
+|GSM8k (5-shot)                   |56.79|
+