Adding Evaluation Results (#2)

- Adding Evaluation Results (a79c60cc5102075969f59803d9733633b733bc46)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,81 +1,222 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - text-generation
+- text-generation
 base_model: JackFram/llama-160m
 datasets:
-  - ehartford/wizard_vicuna_70k_unfiltered
-  - totally-not-an-llm/EverythingLM-data-V3
-  - Open-Orca/SlimOrca-Dedup
-  - databricks/databricks-dolly-15k
-  - THUDM/webglm-qa
+- ehartford/wizard_vicuna_70k_unfiltered
+- totally-not-an-llm/EverythingLM-data-V3
+- Open-Orca/SlimOrca-Dedup
+- databricks/databricks-dolly-15k
+- THUDM/webglm-qa
 widget:
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant, who answers with empathy.<|im_end|>
-      <|im_start|>user
-      Got a question for you!<|im_end|>
-      <|im_start|>assistant
-      Sure! What's it?<|im_end|>
-      <|im_start|>user
-      Why do you love cats so much!? 🐈<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who answers user's questions with empathy.<|im_end|>
-      <|im_start|>user
-      Who is Mona Lisa?<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who provides concise responses.<|im_end|>
-      <|im_start|>user
-      Heya!<|im_end|>
-      <|im_start|>assistant
-      Hi! How may I help you today?<|im_end|>
-      <|im_start|>user
-      I need to build a simple website. Where should I start learning about web development?<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>user
-      Invited some friends to come home today. Give me some ideas for games to play with them!<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who answers user's questions with details and curiosity.<|im_end|>
-      <|im_start|>user
-      What are some potential applications for quantum computing?<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who gives creative responses.<|im_end|>
-      <|im_start|>user
-      Write the specs of a game about mages in a fantasy world.<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who answers user's questions with details.<|im_end|>
-      <|im_start|>user
-      Tell me about the pros and cons of social media.<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who answers user's questions with confidence.<|im_end|>
-      <|im_start|>user
-      What is a dog?<|im_end|>
-      <|im_start|>assistant
-      A dog is a four-legged, domesticated animal that is a member of the class Mammalia, which includes all mammals. Dogs are known for their loyalty, playfulness, and ability to be trained for various tasks. They are also used for hunting, herding, and as service animals.<|im_end|>
-      <|im_start|>user
-      What is the color of an apple?<|im_end|>
-      <|im_start|>assistant
+- text: '<|im_start|>system
+
+    You are a helpful assistant, who answers with empathy.<|im_end|>
+
+    <|im_start|>user
+
+    Got a question for you!<|im_end|>
+
+    <|im_start|>assistant
+
+    Sure! What''s it?<|im_end|>
+
+    <|im_start|>user
+
+    Why do you love cats so much!? 🐈<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with empathy.<|im_end|>
+
+    <|im_start|>user
+
+    Who is Mona Lisa?<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who provides concise responses.<|im_end|>
+
+    <|im_start|>user
+
+    Heya!<|im_end|>
+
+    <|im_start|>assistant
+
+    Hi! How may I help you today?<|im_end|>
+
+    <|im_start|>user
+
+    I need to build a simple website. Where should I start learning about web development?<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>user
+
+    Invited some friends to come home today. Give me some ideas for games to play
+    with them!<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with details and curiosity.<|im_end|>
+
+    <|im_start|>user
+
+    What are some potential applications for quantum computing?<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who gives creative responses.<|im_end|>
+
+    <|im_start|>user
+
+    Write the specs of a game about mages in a fantasy world.<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with details.<|im_end|>
+
+    <|im_start|>user
+
+    Tell me about the pros and cons of social media.<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with confidence.<|im_end|>
+
+    <|im_start|>user
+
+    What is a dog?<|im_end|>
+
+    <|im_start|>assistant
+
+    A dog is a four-legged, domesticated animal that is a member of the class Mammalia,
+    which includes all mammals. Dogs are known for their loyalty, playfulness, and
+    ability to be trained for various tasks. They are also used for hunting, herding,
+    and as service animals.<|im_end|>
+
+    <|im_start|>user
+
+    What is the color of an apple?<|im_end|>
+
+    <|im_start|>assistant'
 inference:
   parameters:
     max_new_tokens: 250
     penalty_alpha: 0.5
     top_k: 4
     repetition_penalty: 1.01
+model-index:
+- name: Llama-160M-Chat-v1
+  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: 24.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 35.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 26.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 44.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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: 51.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-160M-Chat-v1
+      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=Felladrin/Llama-160M-Chat-v1
+      name: Open LLM Leaderboard
 ---
 
 # A Llama Chat Model of 160M Parameters
@@ -143,3 +284,17 @@ output = generate(
 
 print(output[0]["generated_text"])
 ```
+
+# [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_Felladrin__Llama-160M-Chat-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |30.27|
+|AI2 Reasoning Challenge (25-Shot)|24.74|
+|HellaSwag (10-Shot)              |35.29|
+|MMLU (5-Shot)                    |26.13|
+|TruthfulQA (0-shot)              |44.16|
+|Winogrande (5-shot)              |51.30|
+|GSM8k (5-shot)                   | 0.00|
+