Locutusque / TPU-AlignmentLinks
Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free
☆232Updated 11 months ago
Alternatives and similar repositories for TPU-Alignment
Users that are interested in TPU-Alignment are comparing it to the libraries listed below
Sorting:
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆83Updated 2 years ago
- Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines☆196Updated last year
- ☆135Updated last year
- ☆94Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆178Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Full finetuning of large language models without large memory requirements☆94Updated last week
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆289Updated 6 months ago
- A bagel, with everything.☆325Updated last year
- Manage scalable open LLM inference endpoints in Slurm clusters☆274Updated last year
- Let's build better datasets, together!☆263Updated 9 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 7 months ago
- ☆416Updated last year
- An introduction to LLM Sampling☆79Updated 9 months ago
- A set of scripts and notebooks on LLM finetunning and dataset creation☆110Updated last year
- Efficient vector database for hundred millions of embeddings.☆208Updated last year
- Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub☆161Updated 2 years ago
- ☆136Updated last month
- ☆88Updated last year
- Tune MPTs☆84Updated 2 years ago
- ☆124Updated 11 months ago
- Maybe the new state of the art vision model? we'll see 🤷♂️☆167Updated last year
- Fast bare-bones BPE for modern tokenizer training☆164Updated 3 months ago
- inference code for mixtral-8x7b-32kseqlen☆102Updated last year
- Simple UI for debugging correlations of text embeddings☆292Updated 4 months ago
- A comprehensive deep dive into the world of tokens☆225Updated last year