Adding Evaluation Results (#1)

- Adding Evaluation Results (b7c49d3b3193aae3fcdec4d97127d9aeb8c29b92)


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

README.md

@@ -1,13 +1,116 @@
 ---
-license: cc-by-nc-sa-4.0
-datasets:
-- ed001/ds-coder-instruct-v1
 language:
 - en
-pipeline_tag: text-generation
+license: cc-by-nc-sa-4.0
 tags:
 - code
 - data science
+datasets:
+- ed001/ds-coder-instruct-v1
+pipeline_tag: text-generation
+model-index:
+- name: datascience-coder-6.7b
+  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: 34.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ed001/datascience-coder-6.7b
+      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: 53.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ed001/datascience-coder-6.7b
+      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: 37.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ed001/datascience-coder-6.7b
+      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: 44.82
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ed001/datascience-coder-6.7b
+      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: 55.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ed001/datascience-coder-6.7b
+      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: 24.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ed001/datascience-coder-6.7b
+      name: Open LLM Leaderboard
 ---
 
 # The Data Science Coder
@@ -60,4 +163,17 @@ The model was trained on the python susbet of the ds-coder-instruct dataset.
 <img src="https://cdn-uploads.huggingface.co/production/uploads/62618f3e6dae705b2567fb13/XNLclcr4KQqtPseGg2Gzn.png" width="90%"/>
 
 ## Contact
-GitHub: [Ea0011](https://github.com/Ea0011)
+GitHub: [Ea0011](https://github.com/Ea0011)
+# [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_ed001__datascience-coder-6.7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |41.99|
+|AI2 Reasoning Challenge (25-Shot)|34.64|
+|HellaSwag (10-Shot)              |53.83|
+|MMLU (5-Shot)                    |37.96|
+|TruthfulQA (0-shot)              |44.82|
+|Winogrande (5-shot)              |55.72|
+|GSM8k (5-shot)                   |24.94|
+