Adding Evaluation Results

README.md

@@ -1,24 +1,5 @@
 ---
-base_model:
-- meta-llama/Llama-3.1-8B-Instruct
-- ValiantLabs/Llama3.1-8B-Enigma
-- ValiantLabs/Llama3.1-8B-ShiningValiant2
 library_name: transformers
-model-index:
-- name: Llama3.1-8B-PlumCode
-  results:
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: Winogrande (5-Shot)
-      type: Winogrande
-      args:
-        num_few_shot: 5
-    metrics:
-    - type: acc
-      value: 73.16
-      name: acc
 tags:
 - mergekit
 - merge
@@ -52,7 +33,117 @@ tags:
 - conversational
 - chat
 - instruct
-
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+- ValiantLabs/Llama3.1-8B-Enigma
+- ValiantLabs/Llama3.1-8B-ShiningValiant2
+model-index:
+- name: Llama3.1-8B-PlumCode
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-Shot)
+      type: Winogrande
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 73.16
+      name: acc
+  - 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: 20.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumCode
+      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: 8.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumCode
+      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: 2.42
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumCode
+      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: 3.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumCode
+      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: 8.97
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumCode
+      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: 14.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/Llama3.1-8B-PlumCode
+      name: Open LLM Leaderboard
 ---
 # PlumCode
 
@@ -90,3 +181,17 @@ models:
 base_model: meta-llama/Llama-3.1-8B-Instruct
 
 ```
+
+# [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_sequelbox__Llama3.1-8B-PlumCode)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 9.77|
+|IFEval (0-Shot)    |20.45|
+|BBH (3-Shot)       | 8.50|
+|MATH Lvl 5 (4-Shot)| 2.42|
+|GPQA (0-shot)      | 3.47|
+|MuSR (0-shot)      | 8.97|
+|MMLU-PRO (5-shot)  |14.84|
+