add measurement.json

README.md

@@ -0,0 +1,155 @@
+---
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- v000000/Qwen2.5-Lumen-14B
+- arcee-ai/SuperNova-Medius
+- Qwen/Qwen2.5-14B
+- rombodawg/Rombos-LLM-V2.6-Qwen-14b
+- Qwen/Qwen2.5-14B-Instruct
+- EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0
+model-index:
+- name: Qwen2.5-14B-Wernicke
+  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: 52.35
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
+      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: 50.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
+      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: 30.06
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
+      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: 19.13
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
+      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: 18.25
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
+      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: 49.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
+      name: Open LLM Leaderboard
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [v000000/Qwen2.5-Lumen-14B](https://huggingface.co/v000000/Qwen2.5-Lumen-14B)
+* [arcee-ai/SuperNova-Medius](https://huggingface.co/arcee-ai/SuperNova-Medius)
+* [rombodawg/Rombos-LLM-V2.6-Qwen-14b](https://huggingface.co/rombodawg/Rombos-LLM-V2.6-Qwen-14b)
+* [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)
+* [EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0
+  - model: Qwen/Qwen2.5-14B-Instruct
+  - model: arcee-ai/SuperNova-Medius
+  - model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
+  - model: v000000/Qwen2.5-Lumen-14B
+base_model: Qwen/Qwen2.5-14B
+merge_method: model_stock
+dtype: bfloat16
+```
+
+# [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_CultriX__Qwen2.5-14B-Wernicke)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.60|
+|IFEval (0-Shot)    |52.35|
+|BBH (3-Shot)       |50.64|
+|MATH Lvl 5 (4-Shot)|30.06|
+|GPQA (0-shot)      |19.13|
+|MuSR (0-shot)      |18.25|
+|MMLU-PRO (5-shot)  |49.15|
+