SemanticScuttle - klotz.me

klotz: fine-tuning*

Bookmarks on this page are managed by an admin user.

0 bookmark(s) - Sort by: Date / Title ↑ / - Bookmarks from other users for this tag

1. Finetune LLMs on your own consumer hardware using tools from PyTorch and Hugging Face ecosystem | PyTorch

   efficient method for fine-tuning LLM using LoRA and QLoRA, making it possible to train them even on consumer hardware

   2024-01-12 Tags: llm, fine tuning, qlora, lora, peft, pytorch, hugging face, fine-tuning, llms by klotz
2. How to Generate Instruction Datasets from Any Documents for LLM Fine-Tuning

   Generate instruction datasets for fine-tuning Large Language Models (LLMs) using lightweight libraries and documents.

   2024-04-04 Tags: llm, fine-tuning, instruction datasets, towardsdatascience by klotz
3. Improve LLMs with Proxy Tuning

   In this tutorial, learn how to improve the performance of large language models (LLMs) by utilizing a proxy tuning approach, which enables more efficient fine-tuning and better integration with the AI model.

   2024-05-11 Tags: llm, proxy, tuning, fine-tuning by klotz
4. Proxy Fine-Tuning LLMs

   - Proxy fine-tuning is a method to improve large pre-trained language models without directly accessing their weights.
   - It operates on top of black-box LLMs by utilizing only their predictions.
   - The approach combines elements of retrieval-based techniques, fine-tuning, and domain-specific adaptations.
   - Proxy fine-tuning can be used to achieve the performance of heavily-tuned large models by only tuning smaller models.

   2024-05-11 Tags: proxy, fine-tuning, llm, retrieval-augmented generation, domain-specific adaptations, data delivery, rag, catastrophic forgetting, drift by klotz
5. [2401.00908] DocLLM: A layout-aware generative language model for multimodal document understanding

   DocLLM is a lightweight extension to traditional LLMs for reasoning over visual documents, considering both textual semantics and spatial layout. It avoids expensive image encoders and focuses on bounding box information. It outperforms SotA LLMs on 14 out of 16 datasets across all tasks and generalizes well to previously unseen datasets.
   
   Keywords:

   2024-01-06 Tags: docllm, large language models, visual documents, textual semantics, spatial layout, pre-training, fine-tuning by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0