Adding Evaluation Results (#1)

- Adding Evaluation Results (bbfabe136197aafa2bc0da3ac6eb441ca3b03ccf)
- Update README.md (e375c4487c7bdc1253ed7babee81955da66dd25b)


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

README.md

@@ -1,58 +1,163 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - text-generation
-base_model: JackFram/llama-68m
+- text-generation
 datasets:
-  - THUDM/webglm-qa
-  - databricks/databricks-dolly-15k
-  - cognitivecomputations/wizard_vicuna_70k_unfiltered
-  - totally-not-an-llm/EverythingLM-data-V3
-  - Amod/mental_health_counseling_conversations
-  - sablo/oasst2_curated
-  - starfishmedical/webGPT_x_dolly
-  - Open-Orca/OpenOrca
-  - mlabonne/chatml_dpo_pairs
+- THUDM/webglm-qa
+- databricks/databricks-dolly-15k
+- cognitivecomputations/wizard_vicuna_70k_unfiltered
+- totally-not-an-llm/EverythingLM-data-V3
+- Amod/mental_health_counseling_conversations
+- sablo/oasst2_curated
+- starfishmedical/webGPT_x_dolly
+- Open-Orca/OpenOrca
+- mlabonne/chatml_dpo_pairs
+base_model: JackFram/llama-68m
 widget:
-  - text: |-
-      <|im_start|>system
-      You are a knowledgeable assistant. Help the user as much as you can.<|im_end|>
-      <|im_start|>user
-      How to become healthier?<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.<|im_end|>
-      <|im_start|>user
-      Heya!<|im_end|>
-      <|im_start|>assistant
-      Hi! How may I help you?<|im_end|>
-      <|im_start|>user
-      I am interested in developing a career in software engineering. What would you recommend me to do?<|im_end|>
-      <|im_start|>assistant
-  - text: |-
-      <|im_start|>system
-      You are a helpful assistant who provides concise responses.<|im_end|>
-      <|im_start|>user
-      Hi!<|im_end|>
-      <|im_start|>assistant
-      Hello there! How may I help you?<|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|>system
-      You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.<|im_end|>
-      <|im_start|>user
-      Write the background story of an RPG game about wizards and dragons in a sci-fi world.<|im_end|>
-      <|im_start|>assistant
+- messages:
+  - role: system
+    content: You are a career counselor. The user will provide you with an individual
+      looking for guidance in their professional life, and your task is to assist
+      them in determining what careers they are most suited for based on their skills,
+      interests, and experience. You should also conduct research into the various
+      options available, explain the job market trends in different industries, and
+      advice on which qualifications would be beneficial for pursuing particular fields.
+  - role: user
+    content: Heya!
+  - role: assistant
+    content: Hi! How may I help you?
+  - role: user
+    content: I am interested in developing a career in software engineering. What
+      would you recommend me to do?
+- messages:
+  - role: system
+    content: You are a knowledgeable assistant. Help the user as much as you can.
+  - role: user
+    content: How to become healthier?
+- messages:
+  - role: system
+    content: You are a helpful assistant who provides concise responses.
+  - role: user
+    content: Hi!
+  - role: assistant
+    content: Hello there! How may I help you?
+  - role: user
+    content: I need to build a simple website. Where should I start learning about web development?
+- messages:
+  - role: system
+    content: You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.
+  - role: user
+    content: Write the background story of an RPG game about wizards and dragons in a sci-fi world.
 inference:
   parameters:
     max_new_tokens: 64
     penalty_alpha: 0.5
     top_k: 4
+model-index:
+- name: Llama-68M-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: 23.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-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: 28.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-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: 25.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-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: 47.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-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: 54.3
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-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-68M-Chat-v1
+      name: Open LLM Leaderboard
 ---
 
 # A Llama Chat Model of 68M Parameters
@@ -88,3 +193,17 @@ inference:
 penalty_alpha: 0.5
 top_k: 4
 ```
+
+## [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-68M-Chat-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |29.72|
+|AI2 Reasoning Challenge (25-Shot)|23.29|
+|HellaSwag (10-Shot)              |28.27|
+|MMLU (5-Shot)                    |25.18|
+|TruthfulQA (0-shot)              |47.27|
+|Winogrande (5-shot)              |54.30|
+|GSM8k (5-shot)                   | 0.00|