Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: llama2
+model-index:
+- name: speechless-mistral-7b-dare-0.85
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 63.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-mistral-7b-dare-0.85
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 84.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-mistral-7b-dare-0.85
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-mistral-7b-dare-0.85
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 50.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-mistral-7b-dare-0.85
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 79.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-mistral-7b-dare-0.85
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 19.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-mistral-7b-dare-0.85
+      name: Open LLM Leaderboard
 ---
 * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-mistral-7B-dare-0.85-AWQ)
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-mistral-7B-dare-0.85-GPTQ)
@@ -21,3 +124,17 @@ weight_mask_rate: 0.85 / use_weight_rescale: True / mask_stratery: random / scal
 | uukuguy/speechless-mistral-dolphin-orca-platypus-samantha-7b | 62.06   | 64.33  | 84.4      | 63.72  | 52.52      | 78.37      | 21.38  |
 |                                                              |         |        |           |        |            |            |        |
 | speechless-mistral-7b-dare-0.85 (Merge 6 DARE models)        | **64.69**   | 63.57  | **84.82**     | **64.29**  | 50.66      | **79.24**      | **45.56**  |
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_speechlessai__speechless-mistral-7b-dare-0.85)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.39|
+|AI2 Reasoning Challenge (25-Shot)|63.31|
+|HellaSwag (10-Shot)              |84.93|
+|MMLU (5-Shot)                    |64.22|
+|TruthfulQA (0-shot)              |50.68|
+|Winogrande (5-shot)              |79.32|
+|GSM8k (5-shot)                   |19.86|
+