Adding Evaluation Results (#1)

- Adding Evaluation Results (2f88ff6dca6bf9aa875f353c1044f2172613ed0c)


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

README.md

@@ -1,5 +1,8 @@
 ---
-base_model:
+tags:
+- merge
+- mergekit
+- lazymergekit
 - nbeerbower/llama-3-stella-8B
 - defog/llama-3-sqlcoder-8b
 - nbeerbower/llama-3-gutenberg-8B
@@ -9,10 +12,7 @@ base_model:
 - mlabonne/ChimeraLlama-3-8B-v3
 - flammenai/Mahou-1.1-llama3-8B
 - KingNish/KingNish-Llama3-8b
-tags:
-- merge
-- mergekit
-- lazymergekit
+base_model:
 - nbeerbower/llama-3-stella-8B
 - defog/llama-3-sqlcoder-8b
 - nbeerbower/llama-3-gutenberg-8B
@@ -22,6 +22,101 @@ tags:
 - mlabonne/ChimeraLlama-3-8B-v3
 - flammenai/Mahou-1.1-llama3-8B
 - KingNish/KingNish-Llama3-8b
+model-index:
+- name: llama-3-luminous-merged
+  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: 43.23
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3-luminous-merged
+      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: 30.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3-luminous-merged
+      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: 7.85
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3-luminous-merged
+      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: 5.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3-luminous-merged
+      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: 10.63
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3-luminous-merged
+      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: 30.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3-luminous-merged
+      name: Open LLM Leaderboard
 ---
 
 # llama-3-luminous-merged
@@ -107,4 +202,17 @@ 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_BlackBeenie__llama-3-luminous-merged)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.48|
+|IFEval (0-Shot)    |43.23|
+|BBH (3-Shot)       |30.64|
+|MATH Lvl 5 (4-Shot)| 7.85|
+|GPQA (0-shot)      | 5.70|
+|MuSR (0-shot)      |10.63|
+|MMLU-PRO (5-shot)  |30.81|
+