Adding Evaluation Results

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- flammenai/flammen15-gutenberg-DPO-v1-7B
-- Eric111/CatunaLaserPi
 tags:
 - merge
 - mergekit
 - lazymergekit
 - flammenai/flammen15-gutenberg-DPO-v1-7B
 - Eric111/CatunaLaserPi
+base_model:
+- flammenai/flammen15-gutenberg-DPO-v1-7B
+- Eric111/CatunaLaserPi
+model-index:
+- name: GutenLaserPi
+  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: 42.27
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Stark2008/GutenLaserPi
+      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: 32.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Stark2008/GutenLaserPi
+      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: 7.18
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Stark2008/GutenLaserPi
+      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: 4.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Stark2008/GutenLaserPi
+      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: 16.99
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Stark2008/GutenLaserPi
+      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: 23.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Stark2008/GutenLaserPi
+      name: Open LLM Leaderboard
 ---
 
 If you're interested in my models, you can vote for them to be evaluated on the [Leadarboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard).
@@ -62,4 +157,17 @@ pipeline = transformers.pipeline(
 
 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_Stark2008__GutenLaserPi)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.29|
+|IFEval (0-Shot)    |42.27|
+|BBH (3-Shot)       |32.98|
+|MATH Lvl 5 (4-Shot)| 7.18|
+|GPQA (0-shot)      | 4.92|
+|MuSR (0-shot)      |16.99|
+|MMLU-PRO (5-shot)  |23.40|
+