Adding Evaluation Results

README.md

@@ -1,8 +1,10 @@
 ---
 language:
 - en
+license: apache-2.0
 library_name: transformers
-pipeline_tag: text-generation
+tags:
+- code
 datasets:
 - jondurbin/airoboros-2.2.1
 - Open-Orca/OpenOrca
@@ -10,22 +12,120 @@ datasets:
 - ehartford/samantha-data
 - CollectiveCognition/chats-data-2023-09-27
 - stingning/ultrachat
-tags:
-- code
-license: apache-2.0
+pipeline_tag: text-generation
 model-index:
 - name: SpeechlessCoder
   results:
   - task:
       type: text-generation
     dataset:
-      type: openai_humaneval
       name: HumanEval
+      type: openai_humaneval
     metrics:
-    - name: pass@1
-      type: pass@1
+    - type: pass@1
       value: 0.0
+      name: pass@1
       verified: false
+  - 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: 22.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-mistral-six-in-one-7b-orth-1.0
+      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: 25.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-mistral-six-in-one-7b-orth-1.0
+      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: 23.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-mistral-six-in-one-7b-orth-1.0
+      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: 0.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-mistral-six-in-one-7b-orth-1.0
+      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: 49.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-mistral-six-in-one-7b-orth-1.0
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-mistral-six-in-one-7b-orth-1.0
+      name: Open LLM Leaderboard
 ---
 
 <p><h1> speechless-mistral-six-in-one-7b-orth-1.0 </h1></p>
@@ -133,3 +233,17 @@ Mistral 7B is a pretrained base model and therefore does not have any moderation
 ## The Mistral AI Team
  
 Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.`
+
+# [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_uukuguy__speechless-mistral-six-in-one-7b-orth-1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |20.07|
+|AI2 Reasoning Challenge (25-Shot)|22.70|
+|HellaSwag (10-Shot)              |25.04|
+|MMLU (5-Shot)                    |23.12|
+|TruthfulQA (0-shot)              | 0.00|
+|Winogrande (5-shot)              |49.57|
+|GSM8k (5-shot)                   | 0.00|
+