Adding Evaluation Results (#4)

- Adding Evaluation Results (436372398ae579b63526c9b28038290e1554158b)


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

README.md

@@ -7,6 +7,109 @@ tags:
 - Solar Moe
 - Solar
 - Umbra
+model-index:
+- name: Umbra-v2.1-MoE-4x10.7
+  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: 69.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v2.1-MoE-4x10.7
+      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: 87.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v2.1-MoE-4x10.7
+      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: 66.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v2.1-MoE-4x10.7
+      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: 66.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v2.1-MoE-4x10.7
+      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: 83.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v2.1-MoE-4x10.7
+      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: 68.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v2.1-MoE-4x10.7
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/hen3fNHRD7BCPvd2KkfjZ.png)
@@ -129,4 +232,17 @@ 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_Steelskull__Umbra-v2.1-MoE-4x10.7)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.59|
+|AI2 Reasoning Challenge (25-Shot)|69.11|
+|HellaSwag (10-Shot)              |87.57|
+|MMLU (5-Shot)                    |66.48|
+|TruthfulQA (0-shot)              |66.57|
+|Winogrande (5-shot)              |83.11|
+|GSM8k (5-shot)                   |68.69|
+