Adding Evaluation Results (#3)

- Adding Evaluation Results (e1d88c7a02eb5d41441e60397eeb4699f39421e3)


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

README.md

@@ -15,6 +15,109 @@ base_model:
 - FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B
 - SanjiWatsuki/Kunoichi-DPO-v2-7B
 - OmnicromsBrain/NeuralStar-7b-Lazy
+model-index:
+- name: NeuralStar_AlphaWriter_4x7b
+  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: 70.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
+      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: 88.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
+      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: 64.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
+      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: 71.7
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
+      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: 82.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
+      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: 63.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c70c9e21d80a923d664563/ntyev6qExGVY3Ysg2D6-l.png)
@@ -104,3 +207,17 @@ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_ge
 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/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OmnicromsBrain__NeuralStar_AlphaWriter_4x7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.31|
+|AI2 Reasoning Challenge (25-Shot)|70.22|
+|HellaSwag (10-Shot)              |88.31|
+|MMLU (5-Shot)                    |64.60|
+|TruthfulQA (0-shot)              |71.70|
+|Winogrande (5-shot)              |82.00|
+|GSM8k (5-shot)                   |63.00|
+