Adding Evaluation Results

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- NousResearch/Hermes-3-Llama-3.1-70B
-- mlabonne/Llama-3-70B-Instruct-abliterated-LORA
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- NousResearch/Hermes-3-Llama-3.1-70B
+- mlabonne/Llama-3-70B-Instruct-abliterated-LORA
+model-index:
+- name: Hermes-3-Llama-3.1-70B-lorablated
+  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: 71.44
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated
+      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: 52.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated
+      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: 13.82
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated
+      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: 13.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated
+      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: 22.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated
+      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: 41.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated
+      name: Open LLM Leaderboard
 ---
 # 🪽 Hermes-3-Llama-3.1-70B-lorablated
 
@@ -62,4 +156,17 @@ pip install bitsandbytes
 
 # Merge using previous config
 mergekit-yaml config.yaml Hermes-3-Llama-3.1-70B-lorablated --allow-crimes --lora-merge-cache=./cache
-```
+```
+# [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_mlabonne__Hermes-3-Llama-3.1-70B-lorablated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |35.70|
+|IFEval (0-Shot)    |71.44|
+|BBH (3-Shot)       |52.34|
+|MATH Lvl 5 (4-Shot)|13.82|
+|GPQA (0-shot)      |13.20|
+|MuSR (0-shot)      |22.02|
+|MMLU-PRO (5-shot)  |41.37|
+