From 88e0d3f618ca937e96090e38b38fe15354eb7d01 Mon Sep 17 00:00:00 2001 From: Brian Date: Wed, 20 Nov 2024 00:40:40 +1100 Subject: [PATCH] Updated Metadata Override (markdown) --- Metadata-Override.md | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) diff --git a/Metadata-Override.md b/Metadata-Override.md index fd23954..bd8edfd 100644 --- a/Metadata-Override.md +++ b/Metadata-Override.md @@ -89,29 +89,10 @@ As for how this may corresponds with Hugging Face style model cards... consider: ```yaml # Model Card Fields model_name: Example Model Six -model_author: John Smith -model_version: v1.0 -model_organization: SparkExampleMind -model_description: This is an example of a model -model_quantized_by: Abbety Jenson -# Useful for cleanly regenerating default naming conventions -model_finetune: instruct -model_basename: llamabase -model_size_label: 8x2.3Q # Licensing details license: apache-2.0 -license_name: 'Apache License Version 2.0, January 2004' -license_link: 'https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md' -# Model Location/ID -model_url: 'https://huggingface.co/SparkExampleMind/llamabase-8x2.3Q-instruct-v1.0-F16/blob/main/README.md' -model_doi: 'doi:10.1080/02626667.2018.1560449' -model_uuid: f18383df-ceb9-4ef3-b929-77e4dc64787c -model_repo_url: 'https://huggingface.co/SparkExampleMind/llamabase-8x2.3Q-instruct-v1.0-F16' -# Model Source If Conversion -source_model_url: 'https://huggingface.co/SparkExampleMind/llamabase-8x2.3Q-instruct-v1.0-safetensor/blob/main/README.md' -source_model_doi: 'doi:10.1080/02626667.2018.1560449' -source_model_uuid: 'a72998bf-3b84-4ff4-91c6-7a6b780507bc' -source_model_repo_url: 'https://huggingface.co/SparkExampleMind/llamabase-8x2.3Q-instruct-v1.0-safetensor' +license_name: Apache License Version 2.0, January 2004 +license_link: https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md # Model Parents (Merges, Pre-tuning, etc...) base_model_sources: - name: GPT-3 @@ -136,7 +117,7 @@ base_model_sources: dataset_sources: - name: Wikipedia Corpus author: Wikimedia Foundation - version: 2021-06 + version: '2021-06' organization: Wikimedia description: A dataset comprising the full English Wikipedia, used to train models in a range of natural language tasks. url: 'https://dumps.wikimedia.org/enwiki/' @@ -145,7 +126,7 @@ dataset_sources: repo_url: 'https://github.com/wikimedia/wikipedia-corpus' - name: Common Crawl author: Common Crawl Foundation - version: 2021-04 + version: '2021-04' organization: Common Crawl description: A dataset containing web-crawled data from various domains, providing a broad range of text. url: 'https://commoncrawl.org' @@ -159,8 +140,6 @@ tags: - llama - tiny - tiny model -pipeline_tag: - - text-classification language: - en ``` \ No newline at end of file