Adding Evaluation Results (#1)

- Adding Evaluation Results (de6e191270142dd35c547db9a205490b68a8ccd8)

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 tags:
 - merge
 - mergekit
@@ -14,7 +15,6 @@ base_model:
 - Kukedlc/Neural4gsm8k
 - Eric111/Mayo
 - Kukedlc/NeuralSirKrishna-7b
-license: apache-2.0
 model-index:
 - name: NeuralSirKrishna-7b
   results:
@@ -32,6 +32,92 @@ model-index:
     - type: acc
       value: 75.21
       name: accuracy
+    - type: acc
+      value: 75.21
+      name: accuracy
+  - 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: 69.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaths-Experiment-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: 87.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaths-Experiment-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: 65.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaths-Experiment-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: 63.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaths-Experiment-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: 82.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaths-Experiment-7b
+      name: Open LLM Leaderboard
 ---
 
 <div style="font-size: 42px; text-align: center;">🤖 NeuralMaths-Experiment-7b 🤖</div>
@@ -104,4 +190,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_Kukedlc__NeuralMaths-Experiment-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.95|
+|AI2 Reasoning Challenge (25-Shot)|69.71|
+|HellaSwag (10-Shot)              |87.48|
+|MMLU (5-Shot)                    |65.01|
+|TruthfulQA (0-shot)              |63.83|
+|Winogrande (5-shot)              |82.48|
+|GSM8k (5-shot)                   |75.21|
+