Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
-license: cc-by-4.0
 language:
 - en
+license: cc-by-4.0
 pipeline_tag: text-generation
+model-index:
+- name: sqlcoder-34b-alpha
+  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: 54.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=defog/sqlcoder-34b-alpha
+      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: 75.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=defog/sqlcoder-34b-alpha
+      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: 54.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=defog/sqlcoder-34b-alpha
+      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: 40.63
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=defog/sqlcoder-34b-alpha
+      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: 73.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=defog/sqlcoder-34b-alpha
+      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: 34.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=defog/sqlcoder-34b-alpha
+      name: Open LLM Leaderboard
 ---
 
 # Defog SQLCoder
@@ -79,3 +182,17 @@ SQLCoder-34B has been tested on a 4xA10 GPU with `float16` weights. You can also
 - [x] Train the model on more data, with higher data variance
 - [ ] Tune the model further with Reward Modelling and RLHF
 - [ ] Pretrain a model from scratch that specializes in SQL analysis
+
+# [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_defog__sqlcoder-34b-alpha)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |55.59|
+|AI2 Reasoning Challenge (25-Shot)|54.18|
+|HellaSwag (10-Shot)              |75.93|
+|MMLU (5-Shot)                    |54.42|
+|TruthfulQA (0-shot)              |40.63|
+|Winogrande (5-shot)              |73.48|
+|GSM8k (5-shot)                   |34.87|
+