Adding Evaluation Results (#2)

- Adding Evaluation Results (9ce01e84005df24ad40b742ca528bb9f2f0dc992)


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

README.md

@@ -1,10 +1,105 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
 base_model:
-  - nbeerbower/flammen15-mistral-7B
+- nbeerbower/flammen15-mistral-7B
 datasets:
 - jondurbin/gutenberg-dpo-v0.1
+model-index:
+- name: flammen15-gutenberg-DPO-v1-7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 47.98
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 32.67
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 6.72
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 4.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 12.53
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 24.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://huggingface.co/nbeerbower/flammen13X-mistral-7B/resolve/main/flammen13x.png)
@@ -82,4 +177,17 @@ dpo_trainer = DPOTrainer(
 
 # Fine-tune model with DPO
 dpo_trainer.train()
-```
+```
+# [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_flammenai__flammen15-gutenberg-DPO-v1-7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.46|
+|IFEval (0-Shot)    |47.98|
+|BBH (3-Shot)       |32.67|
+|MATH Lvl 5 (4-Shot)| 6.72|
+|GPQA (0-shot)      | 4.59|
+|MuSR (0-shot)      |12.53|
+|MMLU-PRO (5-shot)  |24.29|
+