Adding Evaluation Results

README.md

@@ -1,10 +1,12 @@
 ---
-license: apache-2.0
-datasets:
-- Locutusque/hercules-v1.0
 language:
 - en
+license: apache-2.0
+tags:
+- moe
 base_model: M4-ai/TinyMistral-6x248M
+datasets:
+- Locutusque/hercules-v1.0
 inference:
   parameters:
     do_sample: true
@@ -14,21 +16,126 @@ inference:
     max_new_tokens: 250
     repetition_penalty: 1.1
 widget:
-- text: |
-    <|im_start|>user
+- text: '<|im_start|>user
+
     Write me a Python program that calculates the factorial of n. <|im_end|>
+
     <|im_start|>assistant
-- text: >-
-    An emerging clinical approach to treat substance abuse disorders involves a
-    form of cognitive-behavioral therapy whereby addicts learn to reduce their
-    reactivity to drug-paired stimuli through cue-exposure or extinction
-    training. It is, however,
-- text: |
-    <|im_start|>user
+
+    '
+- text: An emerging clinical approach to treat substance abuse disorders involves
+    a form of cognitive-behavioral therapy whereby addicts learn to reduce their reactivity
+    to drug-paired stimuli through cue-exposure or extinction training. It is, however,
+- text: '<|im_start|>user
+
     How do I say hello in Spanish? <|im_end|>
+
     <|im_start|>assistant
-tags:
-- moe
+
+    '
+model-index:
+- name: TinyMistral-6x248M-Instruct
+  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: 22.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/TinyMistral-6x248M-Instruct
+      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: 27.02
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/TinyMistral-6x248M-Instruct
+      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: 24.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/TinyMistral-6x248M-Instruct
+      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: 43.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/TinyMistral-6x248M-Instruct
+      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: 50.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/TinyMistral-6x248M-Instruct
+      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=M4-ai/TinyMistral-6x248M-Instruct
+      name: Open LLM Leaderboard
 ---
 # Model Card for M4-ai/TinyMistral-6x248M-Instruct
 
@@ -95,4 +202,17 @@ The model has been fine-tuned on the hercules-v1.0 dataset, which contains conte
 
 ## Contributions
 
-Thanks to @jtatman, @aloobun, @Felladrin, and @Locutusque for their contributions to this model.
+Thanks to @jtatman, @aloobun, @Felladrin, and @Locutusque for their contributions to this model.
+# [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_M4-ai__TinyMistral-6x248M-Instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |27.89|
+|AI2 Reasoning Challenge (25-Shot)|22.44|
+|HellaSwag (10-Shot)              |27.02|
+|MMLU (5-Shot)                    |24.13|
+|TruthfulQA (0-shot)              |43.16|
+|Winogrande (5-shot)              |50.59|
+|GSM8k (5-shot)                   | 0.00|
+