Skip to main content
Shourya Shashank
Maintainer of Predacons
View all authors

v0.0.127

· 3 min read
Shourya Shashank
Maintainer of Predacons
  • New Features

    • Introduced streaming capabilities for text and chat generation, allowing real-time output.
    • Added new functions: text_stream and chat_stream for enhanced streaming functionality.
  • Bug Fixes

v0.0.128

· 3 min read
Shourya Shashank
Maintainer of Predacons
  • New Features

    • Introduced streaming capabilities for text and chat generation, allowing real-time output.
    • Added new functions: text_stream and chat_stream for enhanced streaming functionality.
  • Bug Fixes

v0.0.126

· One min read
Shourya Shashank
Maintainer of Predacons

New Features

  • Incremented version number of the predacons package to 0.0.126.
  • Introduced the PredaconsEmbedding class for generating sentence embeddings using a pre-trained transformer model.
  • Bug Fixes

v0.0.125

· One min read
Shourya Shashank
Maintainer of Predacons

Introduced a new keyword argument dont_print_output in the chat generation function for improved output management. Version Updates

v0.0.124

· One min read
Shourya Shashank
Maintainer of Predacons
  • Added auto quantize for generation models reducing the max memory requirement by 4 folds

example

# load model with auto_quantize
model = predacons.load_model(model_name,auto_quantize="4bit")

v0.0.123

· One min read
Shourya Shashank
Maintainer of Predacons
  • added support for gguf model files
model = predacons.load_model(model_path=model_id, gguf_file=gguf_file)
tokenizer = predacons.load_tokenizer(model_id, gguf_file=gguf_file)

v0.0.122

· One min read
Shourya Shashank
Maintainer of Predacons

Added

  • Introduced a new chat generation feature.
    • Added predacons.chat_generate method to generate chat responses using trained models.
    • Example usage:

v0.0.121

· One min read
Shourya Shashank
Maintainer of Predacons

Added

  • Introduced a new chat generation feature.
    • Added predacons.chat_generate method to generate chat responses using trained models.
    • Example usage: