Update README.md

README.md

@@ -1,100 +1,5 @@
 ---
-license: llama3.1
-model-index:
-- name: Llama-Spark
-  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: 79.11
-      name: strict accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Llama-Spark
-      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: 29.77
-      name: normalized accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Llama-Spark
-      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: 1.06
-      name: exact match
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Llama-Spark
-      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: 6.6
-      name: acc_norm
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Llama-Spark
-      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: 2.62
-      name: acc_norm
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Llama-Spark
-      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: 30.23
-      name: accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=arcee-ai/Llama-Spark
-      name: Open LLM Leaderboard
+license: llama3
 ---
 <div align="center">
   <img src="https://i.ibb.co/9hwFrvL/BLMs-Wkx-NQf-W-46-FZDg-ILhg.jpg" alt="Arcee Spark" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
@@ -119,10 +24,16 @@ Llama-Spark is intended for use in conversational AI applications, such as chatb
 
 Llama-Spark is built upon the Llama-3.1-8B base model, fine-tuned using of the Tome Dataset and merged with Llama-3.1-8B-Instruct.
 ## Evaluation Results
-Please note that these scores are consistantly higher than the OpenLLM leaderboard, and should be compared to their relative performance increase not weighed against the leaderboard.
-<div align="center">
-  <img src="https://i.ibb.co/pfSGLtB/Screenshot-2024-08-01-at-11-40-42-PM.png" alt="Arcee Spark" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
-</div>
+We have removed our initial benchmark results and replaced them with the results from the OpenLLM Leaderboard, which are much more deterministic:
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.90|
+|IFEval (0-Shot)    |79.11|
+|BBH (3-Shot)       |29.77|
+|MATH Lvl 5 (4-Shot)| 1.06|
+|GPQA (0-shot)      | 6.60|
+|MuSR (0-shot)      | 2.62|
+|MMLU-PRO (5-shot)  |30.23|
 
 ## Acknowledgements
 
@@ -139,5 +50,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MATH Lvl 5 (4-Shot)| 1.06|
 |GPQA (0-shot)      | 6.60|
 |MuSR (0-shot)      | 2.62|
-|MMLU-PRO (5-shot)  |30.23|
-
+|MMLU-PRO (5-shot)  |30.23|