Adding Evaluation Results

README.md

@@ -1,6 +1,8 @@
 ---
-base_model:
-- Qwen/Qwen2.5-14B-Instruct
+language:
+- en
+- ru
+license: apache-2.0
 tags:
 - text-generation-inference
 - transformers
@@ -12,11 +14,104 @@ tags:
 - ehristoforu
 - trl
 - sft
-license: apache-2.0
-language:
-- en
-- ru
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
 pipeline_tag: text-generation
+model-index:
+- name: RQwen-v0.1
+  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: 76.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/RQwen-v0.1
+      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: 48.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/RQwen-v0.1
+      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: 2.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/RQwen-v0.1
+      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: 10.07
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/RQwen-v0.1
+      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: 10.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/RQwen-v0.1
+      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: 46.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ehristoforu/RQwen-v0.1
+      name: Open LLM Leaderboard
 ---
 # **RQwen** v0.1
 
@@ -30,4 +125,17 @@ pipeline_tag: text-generation
 - **License**: Apache-2.0
 
 
-### GGUF format: *coming soon...*
+### GGUF format: *coming soon...*
+# [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_ehristoforu__RQwen-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |32.48|
+|IFEval (0-Shot)    |76.25|
+|BBH (3-Shot)       |48.49|
+|MATH Lvl 5 (4-Shot)| 2.95|
+|GPQA (0-shot)      |10.07|
+|MuSR (0-shot)      |10.44|
+|MMLU-PRO (5-shot)  |46.69|
+