Adding Evaluation Results (#1)

- Adding Evaluation Results (fa8d3cf907044c07035c670b86781157390df33a)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - text-generation-inference
@@ -7,17 +9,110 @@ tags:
 - llama
 - gguf
 - Llama-3.1-8B
+base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
 datasets:
 - Lyte/Reasoner-1o1-v0.3-HQ
-language:
-- en
-base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
 widget:
-  - example_title: HELP its a Llama
-    messages:
-      - role: user
-        content: "There's a llama on my lawn, how can I get rid of him?"
+- example_title: HELP its a Llama
+  messages:
+  - role: user
+    content: There's a llama on my lawn, how can I get rid of him?
 pipeline_tag: text-generation
+model-index:
+- name: Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+  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: 70.98
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+      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: 27.84
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+      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: 14.8
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+      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: 2.68
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+      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: 4.9
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+      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: 29.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -83,3 +178,17 @@ You are a world-class AI system, capable of complex reasoning and reflection and
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# [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_Lyte__Llama-3.1-8B-Instruct-Reasoner-1o1_v0.3)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.05|
+|IFEval (0-Shot)    |70.98|
+|BBH (3-Shot)       |27.84|
+|MATH Lvl 5 (4-Shot)|14.80|
+|GPQA (0-shot)      | 2.68|
+|MuSR (0-shot)      | 4.90|
+|MMLU-PRO (5-shot)  |29.09|
+