add measurement.json

README.md

@@ -0,0 +1,132 @@
+---
+license: apache-2.0
+library_name: transformers
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
+model-index:
+- name: Rombos-LLM-V2.6-Qwen-14b
+  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: 52.14
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 49.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 28.85
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 17.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 19.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 48.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      name: Open LLM Leaderboard
+---
+# Rombos-LLM-V2.5-Qwen-14b 
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/LbnAeRIHQhRH_dVxfcHOw.jpeg)
+
+Rombos-LLM-V2.6-Qwen-14b is the upgraded version of "rombodawg/Rombos-LLM-V2.5-Qwen-14b". The magic I performed to make this model better than it already was is only known to the Deepest state, dankest memers and God himself, so dont ask 😉. But it does perform a decent bit better than version 2.5 from my hand testing. Benchmarks will come later.
+
+Check out the Continuous Finetuning method that I apply to all my models bellow:
+
+- https://docs.google.com/document/d/1OjbjU5AOz4Ftn9xHQrX3oFQGhQ6RDUuXQipnQ9gn6tU/edit?usp=sharing
+
+Quants:
+
+- https://huggingface.co/rombodawg/Rombos-LLM-V2.6-Qwen-14b-Q8_0-GGUF
+
+- https://huggingface.co/rombodawg/Rombos-LLM-V2.6-Qwen-14b-Q5_K_M-GGUF
+
+- https://huggingface.co/bartowski/Rombos-LLM-V2.6-Qwen-14b-GGUF
+
+Benchmarks: 
+# [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_rombodawg__Rombos-LLM-V2.6-Qwen-14b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |35.89|
+|IFEval (0-Shot)    |52.14|
+|BBH (3-Shot)       |49.22|
+|MATH Lvl 5 (4-Shot)|28.85|
+|GPQA (0-shot)      |17.00|
+|MuSR (0-shot)      |19.26|
+|MMLU-PRO (5-shot)  |48.85|