Adding Evaluation Results

README.md

@@ -1,4 +1,7 @@
 ---
+language:
+- en
+license: llama3
 tags:
 - not-for-all-audiences
 - merge
@@ -51,9 +54,101 @@ base_model:
 - princeton-nlp/Llama-3-Instruct-8B-SimPO
 - chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
 - chargoddard/prometheus-2-llama-3-8b
-license: llama3
-language:
-- en
+model-index:
+- name: LLaMa-3-CursedStock-v2.0-8B
+  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: 63.31
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers/LLaMa-3-CursedStock-v2.0-8B
+      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: 32.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers/LLaMa-3-CursedStock-v2.0-8B
+      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: 8.61
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers/LLaMa-3-CursedStock-v2.0-8B
+      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: 3.24
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers/LLaMa-3-CursedStock-v2.0-8B
+      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: 8.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers/LLaMa-3-CursedStock-v2.0-8B
+      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: 28.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers/LLaMa-3-CursedStock-v2.0-8B
+      name: Open LLM Leaderboard
 ---
 # Merging Compute Sponsored by KoboldAI
 # GGUF Quants by mradermacher
@@ -255,3 +350,17 @@ models:
 #  - Removed ResplendentAI QLoRA models as they were trained on the base, but don't seem to train lm_head or embed_tokens.
 #  - Removed BeaverAI/Llama-3SOME-8B-v2-rc2 as newer versions are out, and idk which is best yet. Also don't want doubledipping if I decide to Beavertrain this.
 ```
+
+# [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_PJMixers__LLaMa-3-CursedStock-v2.0-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.03|
+|IFEval (0-Shot)    |63.31|
+|BBH (3-Shot)       |32.56|
+|MATH Lvl 5 (4-Shot)| 8.61|
+|GPQA (0-shot)      | 3.24|
+|MuSR (0-shot)      | 8.04|
+|MMLU-PRO (5-shot)  |28.40|
+