An innovative library for efficient LLM inference via low-bit quantization

Collection of resources for finetuning Large Language Models (LLMs).

synthetic dataset generation workflow using local file resources for finetuning llms.

Sustain-LC is a benchmarking environment for traditional and reinforcement learning based controls as well as LLM based control

Distributed Reinforcement Learning for LLM Fine-Tuning with multi-GPU utilization

This repository contains code associated with Neuro-LIFT: A Neuromorphic, LLM-based Interactive Framework for Autonomous Drone FlighT at the Edge

A sacred space for heartfelt conversations, where wisdom flows freely and memories gently fade like whispers at sunset.

The Personal Knowledge Graph You Didn’t Know You Already Wrote

Análise Avançada de Dados com Causalidade e Aprendizado por Reforço

Experiments in Latin dactylic hexameter generation with transformers: A hybrid post hoc feedback framework

The course teaches how to fine-tune LLMs using Group Relative Policy Optimization (GRPO)—a reinforcement learning method that improves model reasoning with minimal data. Learn RFT concepts, reward design, LLM-as-a-judge evaluation, and deploy jobs on the Predibase platform.

Fully Connected Neural Networks, Multilayer Neural Networks, MAdaline, CNNs, Segmentation, Detection, RNNs, CNN-LSTM, LSTM, Bi-LSTM, GRU, Transformers, Huber Loss, ViT, DGMs, Triplet VAE, AdvGAN, Image Caption Generation, attention, LLM Fine-Tuning, Soft Prompting, LoRA, Layer Freezing, SlimOrca

FlowerTune LLM on Coding Dataset

ARC-Test-Time-Training (ARC-TTT)

This repository contains all the notebooks, resources, and documentation used to develop and evaluate models for the Automated Essay Scoring (AES) Kaggle competition. The project aims to build an open-source solution for automated essay evaluation to support educators and provide timely feedback to students.

Chaining thoughts and LLMs to learn DNA structural biophysics

A web app for detecting plagiarism between two PDFs. Users can upload PDF files, and the app will detect plagiarism by leveraging a fine-tuned LLM model (SmolLM2-135M) trained on the MIT Plagiarism Detection Dataset. 700+ Monthly Downloads on HuggingFace Model Repo.

Comparing QLoRA, Prompt & Prefix Tuning on Mistral-7B for medical instruction-following

Orion employs mode-specific prompt templates that dynamically incorporate user preferences: Précis Mode: Fast-track synthesis with executive summaries (100-500 words, ~4K tokens) Synopsis Mode: Balanced analytical reports with structured sections (1500-2500 words, ~8K tokens) Treatise Mode: Academic-grade research with abstracts(2000-4000)

FlowerTune LLM on NLP Dataset

No description provided.

Clone your Discord friends with AI!

FlowerTune LLM on Medical Dataset

Daily ML practice notebooks covering tabular data, deep learning, and weekend LLM fine-tuning experiments.

Django implementation of CodeBERT for detecting vulnerable code.

A small dialogue dataset exploring the boundaries of machine decision-making, agency, and alignment. Useful for fine-tuning conversational agents or testing moral reasoning

llm fine tool, faster, saver memory

Schematic Blueprint for Finetuning LLM (e.g. Qwen or Llama) for text classification using LORA. Output model can have original or modified head (e.g. for SequenceClassification).

A comprehensive, production-ready tutorial for fine-tuning Google's FunctionGemma-270M-IT model to build an intelligent E-Commerce Customer Support AI Agent with advanced function calling capabilities.

No description provided.