Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
+language:
+- en
+license: mit
 datasets:
 - Sao10K/Claude-3-Opus-Instruct-15K
 - abacusai/SystemChat-1.1
 - Ba2han/DollyLlama-5k
-language:
-- en
-license: mit
+model-index:
+- name: Llama-Phi-3_DoRA
+  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: 62.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Llama-Phi-3_DoRA
+      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: 79.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Llama-Phi-3_DoRA
+      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: 69.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Llama-Phi-3_DoRA
+      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: 54.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Llama-Phi-3_DoRA
+      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: 73.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Llama-Phi-3_DoRA
+      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: 68.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Llama-Phi-3_DoRA
+      name: Open LLM Leaderboard
 ---
 hf-causal-experimental (pretrained='E:/text-generation-webui/models/phi-984-dora'), limit: None, provide_description: False, num_fewshot: 5, batch_size: None
 |              Task               |Version| Metric |Value |   |Stderr|
@@ -34,3 +137,17 @@ You are a smart, friendly and helpful assistant.
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6324eabf05bd8a54c6eb1650/pJZxrxB1keWNr2Uqw7fkv.png)
 
+
+# [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_Ba2han__Llama-Phi-3_DoRA)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.72|
+|AI2 Reasoning Challenge (25-Shot)|62.29|
+|HellaSwag (10-Shot)              |79.08|
+|MMLU (5-Shot)                    |69.44|
+|TruthfulQA (0-shot)              |54.08|
+|Winogrande (5-shot)              |73.40|
+|GSM8k (5-shot)                   |68.01|
+