Adding Evaluation Results (#1)

- Adding Evaluation Results (176d08b4bc54ef7ac37b5e96a3b5e9204cec2b3b)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -11,6 +11,109 @@ tags:
 - ahxt/LiteLlama-460M-1T
 - ahxt/LiteLlama-460M-1T
 - ahxt/LiteLlama-460M-1T
+model-index:
+- name: KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+  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: 25.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+      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: 38.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+      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: 26.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+      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: 41.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+      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: 50.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
+      name: Open LLM Leaderboard
 ---
 
 # KnowledgeNinja-LiteLlama-460Mx6MoE-1T
@@ -67,4 +170,17 @@ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in
 prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 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_AkiGogikar__KnowledgeNinja-LiteLlama-460Mx6MoE-1T)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |30.23|
+|AI2 Reasoning Challenge (25-Shot)|25.17|
+|HellaSwag (10-Shot)              |38.45|
+|MMLU (5-Shot)                    |26.16|
+|TruthfulQA (0-shot)              |41.57|
+|Winogrande (5-shot)              |50.04|
+|GSM8k (5-shot)                   | 0.00|
+