Adding Evaluation Results (#1)

- Adding Evaluation Results (95bf8c6d2ce34908034ad17e9e18b33ed69cd8a2)


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

README.md

@@ -1,5 +1,100 @@
 ---
 license: apache-2.0
+model-index:
+- name: Mistral-7B-v0.1-signtensors-5-over-16
+  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: 21.18
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16
+      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: 17.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16
+      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: 2.19
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16
+      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: 4.14
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16
+      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: 6.14
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16
+      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: 21.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model Mistral-7B-v0.1-5-over-16
@@ -30,3 +125,17 @@ Use your own risk.
 I have no idea what this model's biases and limitations are.
 I just want to see if the benchmark values are similar to those from `Mistral-7B-v0.1`.
 I am setting up a long computational experiment to test some ideas.
+
+# [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_awnr__Mistral-7B-v0.1-signtensors-5-over-16)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |12.16|
+|IFEval (0-Shot)    |21.18|
+|BBH (3-Shot)       |17.54|
+|MATH Lvl 5 (4-Shot)| 2.19|
+|GPQA (0-shot)      | 4.14|
+|MuSR (0-shot)      | 6.14|
+|MMLU-PRO (5-shot)  |21.75|
+