Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- generated_from_trainer
+- not-for-all-audiences
 license: mit
 datasets:
 - HuggingFaceH4/ultrachat_200k
@@ -9,26 +9,25 @@ language:
 - en
 base_model: mistralai/Mistral-7B-v0.1
 widget:
-  - example_title: Pirate!
-    messages:
-      - role: system
-        content: You are a pirate chatbot who always responds with Arr!
-      - role: user
-        content: "There's a llama on my lawn, how can I get rid of him?"
-    output:
-      text: >-
-        Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare
-        sight, but I've got a plan that might help ye get rid of 'im. Ye'll need
-        to gather some carrots and hay, and then lure the llama away with the
-        promise of a tasty treat. Once he's gone, ye can clean up yer lawn and
-        enjoy the peace and quiet once again. But beware, me hearty, for there
-        may be more llamas where that one came from! Arr!
+- example_title: Pirate!
+  messages:
+  - role: system
+    content: You are a pirate chatbot who always responds with Arr!
+  - role: user
+    content: There's a llama on my lawn, how can I get rid of him?
+  output:
+    text: >-
+      Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare
+      sight, but I've got a plan that might help ye get rid of 'im. Ye'll need
+      to gather some carrots and hay, and then lure the llama away with the
+      promise of a tasty treat. Once he's gone, ye can clean up yer lawn and
+      enjoy the peace and quiet once again. But beware, me hearty, for there may
+      be more llamas where that one came from! Arr!
 pipeline_tag: text-generation
 model-index:
 - name: zephyr-7b-beta
   results:
-  # AI2 Reasoning Challenge (25-Shot)
-  - task: 
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -39,15 +38,14 @@ model-index:
       args:
         num_few_shot: 25
     metrics:
-       - type: acc_norm
-         name: normalized accuracy
-         value: 62.03071672354948
+    - type: acc_norm
+      name: normalized accuracy
+      value: 62.03071672354948
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # HellaSwag (10-shot)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -57,15 +55,14 @@ model-index:
       args:
         num_few_shot: 10
     metrics:
-       - type: acc_norm
-         name: normalized accuracy
-         value: 84.35570603465445
+    - type: acc_norm
+      name: normalized accuracy
+      value: 84.35570603465445
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # DROP (3-shot)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -75,15 +72,14 @@ model-index:
       args:
         num_few_shot: 3
     metrics:
-       - type: f1
-         name: f1 score
-         value: 9.662437080536909
+    - type: f1
+      name: f1 score
+      value: 9.66243708053691
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # TruthfulQA (0-shot)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -94,14 +90,13 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
-       - type: mc2
-         value: 57.44916942762855
+    - type: mc2
+      value: 57.44916942762855
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # GSM8k (5-shot)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -112,15 +107,14 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
-       - type: acc
-         name: accuracy
-         value: 12.736921910538287
+    - type: acc
+      name: accuracy
+      value: 12.736921910538287
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # MMLU (5-Shot)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -131,15 +125,14 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
-       - type: acc
-         name: accuracy
-         value: 61.07
+    - type: acc
+      name: accuracy
+      value: 61.07
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # Winogrande (5-shot)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
@@ -150,38 +143,35 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
-       - type: acc
-         name: accuracy
-         value: 77.74269928966061
+    - type: acc
+      name: accuracy
+      value: 77.7426992896606
     source:
       name: Open LLM Leaderboard
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
-
-  # AlpacaEval (taken from model card)
-  - task: 
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
       name: AlpacaEval
       type: tatsu-lab/alpaca_eval
     metrics:
-       - type: unknown
-         name: win rate
-         value: 0.9060
+    - type: unknown
+      name: win rate
+      value: 0.906
     source:
       url: https://tatsu-lab.github.io/alpaca_eval/
-
-  # MT-Bench (taken from model card)
-  - task: 
+  - task:
       type: text-generation
       name: Text Generation
     dataset:
       name: MT-Bench
       type: unknown
     metrics:
-       - type: unknown
-         name: score
-         value: 7.34
+    - type: unknown
+      name: score
+      value: 7.34
     source:
       url: https://huggingface.co/spaces/lmsys/mt-bench
 ---