license: mit
base_model: microsoft/Phi-3-medium-128k-instruct
library_name: adapters
datasets:
  - awels/ocpvirt_admin_dataset
language:
  - en
widget:
  - text: Who are you, Thready ?
tags:
  - awels
  - redhat
Thready Model Card
Model Details
Model Name: Thready

Model Type: Transformer-based leveraging Microsoft Phi 14b 128k tokens

Publisher: Awels Engineering

License: MIT

Model Description: Thready is a sophisticated model designed to help as an AI agent focusing on the Red Hat Openshift Virtualization solution. It leverages advanced machine learning techniques to provide efficient and accurate solutions. It has been trained on the full docments corpus of OCP Virt 4.16.

Dataset
Dataset Name: awels/ocpvirt_admin_dataset

Dataset Source: Hugging Face Datasets

Dataset License: MIT

Dataset Description: The dataset used to train Thready consists of all the public documents available on Red Hat Openshift Virtualization. This dataset is curated to ensure a comprehensive representation of typical administrative scenarios encountered in Openshift Virtualization.

Training Details
Training Data: The training data includes 70,000 Questions and Answers generated by the Bonito LLM. The dataset is split into 3 sets of data (training, test and validation) to ensure robust model performance.

Training Procedure: Thready was trained using supervised learning with cross-entropy loss and the Adam optimizer. The training involved 1 epoch, a batch size of 4, a learning rate of 5.0e-06, and a cosine learning rate scheduler with gradient checkpointing for memory efficiency.

Hardware: The model was trained on a single NVIDIA H100 SXM graphic card.

Framework: The training was conducted using PyTorch.

Evaluation
Evaluation Metrics: Thready was evaluated on the training dataset:

epoch = 1.0 total_flos = 74851620GF train_loss = 2.6706 train_runtime = 0:41:52.37 train_samples_per_second = 22.229 train_steps_per_second = 5.55epoch                    =         1.0
  total_flos               = 273116814GF
  train_loss               =      1.5825
  train_runtime            =  1:33:44.28
  train_samples_per_second =       9.803
  train_steps_per_second   =       2.451

Performance: The model achieved the following results on the evaluation dataset:

 epoch = 1.0 eval_loss = 2.2243 eval_runtime = 0:02:21.35 eval_samples = 11191 eval_samples_per_second = 97.867 eval_steps_per_second = 24.47

Intended Use
Primary Use Case: Thready is intended to be used locally in an agent swarm to colleborate together to solve Red Hat Openshift Virtualization related problems.

Limitations: While Thready is highly effective, it may have limitations due to the model size. An 8b model based on Llama 3 is used internally at Awels Engineering.