-
Proof of Influence in Large Language Models : POILLMs
This is ai generated with bing based on ramblings from me.
Whitepaper: Proof of Influence in Large Language Models (LLMs)
Abstract
The conce…
-
Consider adding support for [nvidia/Minitron-8B-Base](https://huggingface.co/nvidia/Minitron-8B-Base), it appears to be fairly multilingual (at least better at my native language than most models) but…
-
Hi,
Thanks for the awesome work. Can you please release the code for the language models?
Regards,
Shivam
-
Hello everyone, below is my code for fine-tuning XTTS for a new language. It works well in my case with over 100 hours of audio.
https://github.com/nguyenhoanganh2002/XTTSv2-Finetuning-for-New-Lang…
-
Hello @aluminumbox , I continued training the `llm` model on a German dataset (300 hours), but after 25k steps the model could not pronounce German and the 5 available languages.
My process:
- I f…
-
I attempted to run benchmarks for the llama-3-8b-instruct and llama-3.1-8b-instruct models using both CPU and GPU, but the process failed. (I successfully tested the llama2-7b-chatbot model)
I f…
-
The README mentions this codebase can act as a "reference for enthusiasts keen on pretraining language models under 5 billion parameters". I'm wondering if you could give a brief guide on how to do so…
-
Previously reported in https://github.com/speechmatics/ctranslate2_triton_backend/issues/2#issuecomment-1546889761 by @aamir-s18
The backend currently only supports encoder-decoder models,
whereas…
-
First of all, thank you for this wonderful project!
Is there a reason that some languages with generation 1 models (thai, cyrillic, arabic, etc) don't have corresponding generation 2 models? Were t…
-
https://arxiv.org/pdf/2305.05920.pdf