v.0.1.4

⚠️ Change Log:

• ZeroGPT deprecated
• Minor updates

v.0.1.3

⚠️ Change Log:

• Streaming completion added
• Loading method
• Minor changes

v.0.1.2

⚠️ Change Log:

• Documentation update
• Edit mode updated
• Minor changes

v.0.1.1a

⚠️ Change Log:

• Minor upgrades

v.0.1.1

⚠️ Change Log:

• NEW mode added using GPTZero to analyze AI generated text
• Embedded mode adedd
• Predictable mode added
• Mode selector improved
• Minor changes

Notes:

• Bug fix editable mode

v.0.1.0

⚠️ Change Log:

Test all the available models for code/text/insert/similarity

Modes:

Training mode: Prepare your own sets based on the interaction

Edit mode: First input will be contextual the second one instructional

Conversational mode: A friendly experience with the model

Advanced parameters like:

• Temperature
• Topp
• Penalty
• Frequency penalty
• Max tokens
• Engine
• Multiple results and probabilities
• Detailed log according to UTC
• Export JSON files for training purposes
• Export conversations on TXT

General parameters:

Mode: Modify the actual mode, select between (TEXT/EDIT/CODE)
Engine: Modify the model that you want to test
Results: Modify the amount of results displayed for each prompt
Probabilities: According to your setup of the temperature and topp, probably you will need to use this field to populate a more accurate response according to the possibilities of results
Temperature: If you are working with temperature, try to keep the topp in a higher values than temperature
Topp: Applies the same concept as temperature, when you are modifying this value, you need to apply a higher value for temperature
Penalty: Penalty applied to the characters an redundancy in a result completion
Frequency Penalty: Establish the frequency of the penalty threshold defined

Modes:

Training Mode: Prepare your fine tunning data based on the completion response, can be exported to a JSON file for further use.
Edit Mode: Use Edit mode for all the requests
Press New Conversation and select Edit mode the first request will be for a completion endpoint the second based on the first request will continue editing the content in the parameters that you ask.
Conversational Mode: Use conversational AI mode request for a friendly interaction.

v.0.0.9

⚠️ Change Log:

• Retrieves all the models to work with them in a local sandbox
• Includes validation forms
• Minor changes

v.0.0.8

Change Log:

• Training mode added: With this mode you can create your own sets based on previous interactions, then can be exported to be used as a fine-tunning model, exported on a JSON format same for log entries.
• Conversation are stored as a .txt
• Utility script added
• Log event management added
• Readme updated

v.0.0.7

Change Log:

• Dockerfile
• Build and run scripts

v.0.0.6

#6 Change Log:

• Documentation updated
• Minor improvements