From 94aee83e73da5b32edb861978f84b9c9991161d4 Mon Sep 17 00:00:00 2001 From: Keyi Wang <364059176w@gmail.com> Date: Tue, 28 Jan 2025 11:38:23 -0600 Subject: [PATCH] Contribute Model DeepSeek V3&R1 --- models/DeepSeek-R1.yml | 117 +++++++++++++++++++++++++++++++++++++++++ models/DeepSeek-V3.yml | 117 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 234 insertions(+) create mode 100644 models/DeepSeek-R1.yml create mode 100644 models/DeepSeek-V3.yml diff --git a/models/DeepSeek-R1.yml b/models/DeepSeek-R1.yml new file mode 100644 index 0000000..3069dcc --- /dev/null +++ b/models/DeepSeek-R1.yml @@ -0,0 +1,117 @@ +framework: + name: 'Model Openness Framework' + version: '1.0' + date: '2024-12-15' +release: + name: 'DeepSeek-R1' + version: '671B' + date: '2025-01-20' + type: 'language' + architecture: '' + origin: '' + producer: 'DeepSeek AI' + contact: '' + components: + - + name: 'Model architecture' + description: "Well commented code for the model's architecture" + location: '' + license_name: MIT + license_path: '' + - + name: 'Data preprocessing code' + description: 'Code for data cleansing, normalization, and augmentation' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Training code' + description: 'Code used for training the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Inference code' + description: 'Code used for running the model to make predictions' + location: '' + license_name: MIT + license_path: '' + - + name: 'Evaluation code' + description: 'Code used for evaluating the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Supporting libraries and tools' + description: "Libraries and tools used in the model's development" + location: '' + license_name: MIT + license_path: '' + - + name: 'Model parameters (Final)' + description: 'Trained model parameters, weights and biases' + location: '' + license_name: MIT + license_path: '' + - + name: 'Model parameters (Intermediate)' + description: 'Trained model parameters, weights and biases' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: Datasets + description: 'Training, validation and testing datasets used for the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Evaluation data' + description: 'Data used for evaluating the model' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Model metadata' + description: 'Any model metadata including training configuration and optimizer states' + location: '' + license_name: MIT + license_path: '' + - + name: 'Sample model outputs' + description: 'Examples of outputs generated by the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Model card' + description: 'Model details including performance metrics, intended use, and limitations' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Data card' + description: 'Documentation for datasets including source, characteristics, and preprocessing details' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Technical report' + description: 'Technical report detailing capabilities and usage instructions for the model' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Research paper' + description: 'Research paper detailing the development and capabilities of the model' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Evaluation results' + description: 'The results from evaluating the model' + location: '' + license_name: 'License not specified' + license_path: '' + diff --git a/models/DeepSeek-V3.yml b/models/DeepSeek-V3.yml new file mode 100644 index 0000000..8245db2 --- /dev/null +++ b/models/DeepSeek-V3.yml @@ -0,0 +1,117 @@ +framework: + name: 'Model Openness Framework' + version: '1.0' + date: '2024-12-15' +release: + name: 'DeepSeek-V3' + version: '671B' + date: '2024-12-26' + type: 'language' + architecture: '' + origin: '' + producer: 'DeepSeek AI' + contact: '' + components: + - + name: 'Model architecture' + description: "Well commented code for the model's architecture" + location: '' + license_name: MIT + license_path: '' + - + name: 'Data preprocessing code' + description: 'Code for data cleansing, normalization, and augmentation' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Training code' + description: 'Code used for training the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Inference code' + description: 'Code used for running the model to make predictions' + location: '' + license_name: MIT + license_path: '' + - + name: 'Evaluation code' + description: 'Code used for evaluating the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Supporting libraries and tools' + description: "Libraries and tools used in the model's development" + location: '' + license_name: MIT + license_path: '' + - + name: 'Model parameters (Final)' + description: 'Trained model parameters, weights and biases' + location: '' + license_name: DeepSeek License Agreement + license_path: '' + - + name: 'Model parameters (Intermediate)' + description: 'Trained model parameters, weights and biases' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: Datasets + description: 'Training, validation and testing datasets used for the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Evaluation data' + description: 'Data used for evaluating the model' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Model metadata' + description: 'Any model metadata including training configuration and optimizer states' + location: '' + license_name: DeepSeek License Agreement + license_path: '' + - + name: 'Sample model outputs' + description: 'Examples of outputs generated by the model' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Model card' + description: 'Model details including performance metrics, intended use, and limitations' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Data card' + description: 'Documentation for datasets including source, characteristics, and preprocessing details' + location: '' + license_name: 'Component not included' + license_path: '' + - + name: 'Technical report' + description: 'Technical report detailing capabilities and usage instructions for the model' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Research paper' + description: 'Research paper detailing the development and capabilities of the model' + location: '' + license_name: 'License not specified' + license_path: '' + - + name: 'Evaluation results' + description: 'The results from evaluating the model' + location: '' + license_name: 'License not specified' + license_path: '' +