Adding Evaluation Results (#2)

- Adding Evaluation Results (d031fd883ed62246a960f6100974aa16d058de52)

README.md

@@ -2,6 +2,7 @@
 language:
 - en
 license: apache-2.0
+library_name: transformers
 tags:
 - text-generation-inference
 - transformers
@@ -21,17 +22,6 @@ tags:
 - mega-series
 - SpydazWebAI
 base_model: LeroyDyer/Mixtral_AI_CyberTron_Ultra
-metrics:
-- accuracy
-- bertscore
-- bleu
-- brier_score
-- cer
-- character
-- charcut_mt
-- chrf
-- code_eval
-library_name: transformers
 datasets:
 - gretelai/synthetic_text_to_sql
 - HuggingFaceTB/cosmopedia
@@ -47,6 +37,111 @@ datasets:
 - Rogendo/English-Swahili-Sentence-Pairs
 - ise-uiuc/Magicoder-Evol-Instruct-110K
 - meta-math/MetaMathQA
+metrics:
+- accuracy
+- bertscore
+- bleu
+- brier_score
+- cer
+- character
+- charcut_mt
+- chrf
+- code_eval
+model-index:
+- name: SpydazWeb_AI_CyberTron_Ultra_7b
+  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: 15.56
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+      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: 27.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+      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: 1.36
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+      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=LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+      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: 10.3
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+      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: 20.73
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/SpydazWeb_AI_CyberTron_Ultra_7b
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -116,4 +211,17 @@ Im not sure if Lora actually works when you save them but i do save some and use
 
 This mistral 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)
+[<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/LeroyDyer__SpydazWeb_AI_CyberTron_Ultra_7b-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.57|
+|IFEval (0-Shot)    |15.56|
+|BBH (3-Shot)       |27.75|
+|MATH Lvl 5 (4-Shot)| 1.36|
+|GPQA (0-shot)      | 5.70|
+|MuSR (0-shot)      |10.30|
+|MMLU-PRO (5-shot)  |20.73|
+