Код для файнтюна LM (rugpt, LLaMa, FRED T5) средствами transformers + deepspeed + LoRa
☆14May 22, 2023Updated 2 years ago
Alternatives and similar repositories for LM-finetune
Users that are interested in LM-finetune are comparing it to the libraries listed below
Sorting:
- Russian text segmenter and tokenizer☆18Mar 2, 2021Updated 5 years ago
- ☆21Apr 2, 2025Updated 11 months ago
- ☆17Oct 9, 2023Updated 2 years ago
- Реализация sklearn-based Transformer-а для Weight of Evidence преобразования☆10May 6, 2020Updated 5 years ago
- This is a smart chunker for efficient preparing of long document for RAG☆13Jan 21, 2026Updated last month
- Электронный журнал☆11Dec 22, 2022Updated 3 years ago
- Диалоговая система на базе FRED-T5☆37Jul 10, 2023Updated 2 years ago
- Gazeta: Dataset for automatic summarization of Russian news / Газета: набор данных для автоматического реферирования на русском языке☆36Oct 6, 2021Updated 4 years ago
- ☆11Jan 11, 2022Updated 4 years ago
- DreamSmooth: Improving Model-Based RL with Reward Smoothing (ICLR 2024)☆12May 6, 2024Updated last year
- About Code release for "Imagination Mechanism: Mesh Information Propagation for Enhancing Data Efficiency in Reinforcement Learning"☆13Oct 7, 2023Updated 2 years ago
- code for polite☆11Feb 28, 2024Updated 2 years ago
- ☆16Feb 22, 2025Updated last year
- Teaching a humanoid to walk(ish), then displaying in your browser (using tensorflow.js and reinforcement learning)☆10Sep 7, 2020Updated 5 years ago
- LLM Skirmish☆44Feb 3, 2026Updated last month
- Stickers just for fun☆12Dec 17, 2022Updated 3 years ago
- The code for the paper "A Bayesian Approach to Online Planning" published in ICML 2024.☆13Jun 17, 2024Updated last year
- A collection of heat engines, based on the OpenAI Gym environment framework for use with reinforcement learning applications.☆15Dec 20, 2021Updated 4 years ago
- The official repo for "CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models"☆30Updated this week
- ☆14Mar 21, 2024Updated last year
- A "gym" style toolkit for building lightweight NAS systems.☆13Jun 13, 2022Updated 3 years ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆47Mar 20, 2025Updated 11 months ago
- unifloc on python☆15Nov 14, 2020Updated 5 years ago
- Latest version of Docear re-packaged with old java library to work on Linux without additional configurations.☆10Dec 13, 2020Updated 5 years ago
- Diy gaming steering wheel with feedback. Самодельный игровой руль с обратной связью.☆14Sep 12, 2022Updated 3 years ago
- Official Code Repo for the paper "Learning to Play Atari in a World of Tokens" accepted at ICML, 2024☆11Jun 6, 2024Updated last year
- ReLAx - Reinforcement Learning Applications Library☆15Feb 19, 2023Updated 3 years ago
- Robot simulator using web technologies, just JavaScript☆10Feb 13, 2020Updated 6 years ago
- Bitcoin blockchain to avro file☆12Feb 8, 2018Updated 8 years ago
- Submission Under Review☆17May 15, 2025Updated 9 months ago
- Multilingual RAG benchmark.☆10Nov 22, 2024Updated last year
- Concise Reasoning via Reinforcement Learning☆13Apr 16, 2025Updated 10 months ago
- Neural Networks for penetration testing. Part of active research.☆13Jun 21, 2022Updated 3 years ago
- Агрегированный проект методов искусственного интеллекта и машинного обучения☆11Oct 16, 2017Updated 8 years ago
- Bunch of notebooks for pre-training custom Saiga-like LLM☆12Feb 9, 2024Updated 2 years ago
- A Controllable Model of Grounded Response Generation (AAAI 21)☆13Oct 25, 2022Updated 3 years ago
- My Very Own Deep Multiple Layered Echo State Network☆13Jan 2, 2021Updated 5 years ago
- paper on dexpilot☆15Oct 14, 2019Updated 6 years ago
- [ICML 2023] Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills☆12Jul 15, 2023Updated 2 years ago