geronimi73 / 3090_shortsLinks
minimal scripts for 24GB VRAM GPUs. training, inference, whatever
☆41Updated 3 weeks ago
Alternatives and similar repositories for 3090_shorts
Users that are interested in 3090_shorts are comparing it to the libraries listed below
Sorting:
- Codebase accompanying the Summary of a Haystack paper.☆79Updated 9 months ago
- ☆87Updated last year
- Verifiers for LLM Reinforcement Learning☆64Updated 2 months ago
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆77Updated 8 months ago
- ☆35Updated last year
- ☆48Updated 5 months ago
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- ☆48Updated 10 months ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆64Updated last year
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆79Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆168Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated 10 months ago
- ☆52Updated 8 months ago
- Simple GRPO scripts and configurations.☆59Updated 5 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 5 months ago
- Code for NeurIPS LLM Efficiency Challenge☆59Updated last year
- Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆41Updated 8 months ago
- Multi-Domain Expert Learning☆67Updated last year
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆25Updated last month
- ☆37Updated 2 years ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆132Updated last year
- Evaluating LLMs with CommonGen-Lite☆90Updated last year
- ☆76Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- This is the official repository for Inheritune.☆111Updated 5 months ago
- ☆62Updated 11 months ago
- A pipeline for LLM knowledge distillation☆105Updated 3 months ago
- Data preparation code for Amber 7B LLM☆91Updated last year
- ☆27Updated last week