Update README.md

README.md

@@ -1,60 +1,83 @@
+---
 license: mit
-base_model: microsoft/Phi-3-medium-128k-instruct
+base_model: microsoft/Phi-3-mini-128k-instruct
 library_name: adapters
 datasets:
-  - awels/ocpvirt_admin_dataset
+- awels/ocpvirt_admin_dataset
 language:
-  - en
+- en
 widget:
-  - text: Who are you, Thready ?
+- text: Who are you, Thready ?
 tags:
-  - awels
-  - redhat
-Thready Model Card
-Model Details
-Model Name: Thready
+- awels
+- redhat
+---
 
-Model Type: Transformer-based leveraging Microsoft Phi 14b 128k tokens
+# Thready Model Card
 
-Publisher: Awels Engineering
+## Model Details
+**Model Name:** Thready
 
-License: MIT
+**Model Type:** Transformer-based leveraging Microsoft Phi 3b 128k tokens
 
-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.
+**Publisher:** Awels Engineering
 
-Dataset
-Dataset Name: awels/ocpvirt_admin_dataset
+**License:** MIT
 
-Dataset Source: Hugging Face Datasets
+**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 License: MIT
+## Dataset
+**Dataset Name:** [awels/ocpvirt_admin_dataset](https://huggingface.co/datasets/awels/ocpvirt_admin_dataset)
 
-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.
+**Dataset Source:** Hugging Face Datasets
 
-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.
+**Dataset License:** MIT 
 
-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.
+**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.
 
-Hardware: The model was trained on a single NVIDIA H100 SXM graphic card.
+## Training Details
 
-Framework: The training was conducted using PyTorch.
+**Training Data:**
+The training data includes 70,000 Questions and Answers generated by the [Bonito LLM](https://github.com/BatsResearch/bonito). The dataset is split into 3 sets of data (training, test and validation) to ensure robust model performance.
 
-Evaluation
-Evaluation Metrics: Thready was evaluated on the training dataset:
+**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.
 
-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
+**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               = 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:
+**Performance:**
+The model achieved the following results on the evaluation dataset:
+
+> epoch                   =        1.0
+  eval_loss               =     1.3341
+  eval_runtime            = 0:04:02.02
+  eval_samples            =      11191
+  eval_samples_per_second =     56.469
+  eval_steps_per_second   =     14.118
+
 
- 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
 
-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.
+**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.
+**Limitations:**
+This 14b model is an upscale of the 3b model. Much better loss than the 3b so results should be better.