Predacons

Changelog
Added
- Introduced a new chat generation feature.
- Added `predacons.chat_generate` method to generate chat responses using trained models.
- Example usage:
python
chat = [
{"role": "user", "content": "Hey, what is a car?"}
]
chat_output = predacons.chat_generate(
model=model,
sequence=chat,
max_length=50,
tokenizer=tokenizers,
trust_remote_code=True
)


Updated
- README.md to include documentation and example usage for the new chat generation feature.

What's Changed
* Feature/chat generation by shouryashashank in https://github.com/Predacons/predacons/pull/35


**Full Changelog**: https://github.com/Predacons/predacons/compare/v0.0.121...v0.0.122

Changelog
Added
- Introduced a new chat generation feature.
- Added `predacons.chat_generate` method to generate chat responses using trained models.
- Example usage:
python
chat = [
{"role": "user", "content": "Hey, what is a car?"}
]
chat_output = predacons.chat_generate(
model=model,
sequence=chat,
max_length=50,
tokenizer=tokenizers,
trust_remote_code=True,
apply_chat_template=True
)


Updated
- README.md to include documentation and example usage for the new chat generation feature.


What's Changed
* added docs by shouryashashank in https://github.com/Predacons/predacons/pull/31
* added chat generation by shouryashashank in https://github.com/Predacons/predacons/pull/33
* Feature/chat generation by shouryashashank in https://github.com/Predacons/predacons/pull/34


**Full Changelog**: https://github.com/Predacons/predacons/compare/v0.0.120...v0.0.121

What's Changed
* Create LICENSE-COMMERCIAL-PERPETUAL by shouryashashank in https://github.com/Predacons/predacons/pull/29
* added read csv by shouryashashank in https://github.com/Predacons/predacons/pull/23
* Feature/add csv support by shouryashashank in https://github.com/Predacons/predacons/pull/30
New features
* Added support for csv and json file types
* Added full support for hugging face datasets
* Added automatic formatting function preprocessing function generation for any type of data
* Added proper documentation for all the methods

**Full Changelog**: https://github.com/Predacons/predacons/compare/v0.0.119...v0.0.120

What's Changed
* Feature/generate fix for windows by shouryashashank in https://github.com/Predacons/predacons/pull/28


**Full Changelog**: https://github.com/Predacons/predacons/compare/v0.0.118...v0.0.119

What's Changed
* Create FUNDING.yml by shouryashashank in https://github.com/Predacons/predacons/pull/22
* added try block for fast gen by shouryashashank in https://github.com/Predacons/predacons/pull/26
* Feature/generate fix for windows by shouryashashank in https://github.com/Predacons/predacons/pull/27


**Full Changelog**: https://github.com/Predacons/predacons/compare/v0.0.117...v0.0.118

What's Changed
* Update requirements.txt and setup.py, add new functions by shouryashashank in https://github.com/Predacons/predacons/pull/20
* Update setup.py by shouryashashank in https://github.com/Predacons/predacons/pull/21

- moved to SFTTrainer
- added auto tokenizer
- added auto peft config using laura

- [ ] With this pr we can now train bigger model with very less memory
- [ ] tested training gemma with 4gb vram

**Full Changelog**: https://github.com/Predacons/predacons/compare/v0.0.116...v0.0.117