Adding Evaluation Results (#1)

- Adding Evaluation Results (4f79ab536c9038cf61cf3791afe5d1726a42a78c)


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

README.md

@@ -2,6 +2,109 @@
 license: llama2
 datasets:
 - 922-CA/MoCha_v1
+model-index:
+- name: monika-ddlc-7b-v1
+  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: 54.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/monika-ddlc-7b-v1
+      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: 76.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/monika-ddlc-7b-v1
+      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: 45.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/monika-ddlc-7b-v1
+      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: 43.94
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/monika-ddlc-7b-v1
+      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: 72.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/monika-ddlc-7b-v1
+      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: 8.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/monika-ddlc-7b-v1
+      name: Open LLM Leaderboard
 ---
 # monika-ddlc-7b-v1:
 * LLaMA-2 7b chat fine-tuned for Monika character from DDLC (still somewhat experimental)
@@ -33,4 +136,17 @@ Additionally, being character-focused means that this model may not be the smart
 
 Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk.
 
-Note: Ideally, would have liked to fine-tune on other models (specifically [Zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)). May try soon for later versions.
+Note: Ideally, would have liked to fine-tune on other models (specifically [Zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)). May try soon for later versions.
+# [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_922-CA__monika-ddlc-7b-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |50.49|
+|AI2 Reasoning Challenge (25-Shot)|54.95|
+|HellaSwag (10-Shot)              |76.78|
+|MMLU (5-Shot)                    |45.61|
+|TruthfulQA (0-shot)              |43.94|
+|Winogrande (5-shot)              |72.85|
+|GSM8k (5-shot)                   | 8.79|
+