Старший Авгур

Про локальные языковые модели для относительно неподготовленной аудитории:
Видео: https://youtu.be/KXBRGkZTX1U?si=CyVKSUavsSnZfffR&t=241
Презентация: http://tinyurl.com/gusevlocal
Подкаст: https://mlpodcast.mave.digital/ep-55

Про древнюю генерацию стихов:
Видео: https://www.youtube.com/watch?v=wTN-qKPu4c0
Статья на Хабре: https://habr.com/ru/articles/334046/

Про Сайгу:
Видео: https://www.youtube.com/watch?v=YqKCk8_dNpQ
Презентация: http://tinyurl.com/gusevsaiga
Статья на Хабре: https://habr.com/ru/articles/759386/

Про не-трансформерные модели:
Видео: https://www.youtube.com/watch?v=C65JbhTi-O4
Презентация: https://tinyurl.com/gusevlrnn

Компиляция нескольких постов про то, что читать про ML/NLP/LLM:

Обучающие материалы 🗒
- https://habr.com/ru/articles/774844/
- https://lena-voita.github.io/nlp_course.html
- https://web.stanford.edu/~jurafsky/slp3/ed3book.pdf
- https://www.youtube.com/watch?v=rmVRLeJRkl4&list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4
- https://huggingface.co/docs/transformers/perf_train_gpu_one

Блоги 🍿
- https://huggingface.co/blog/
- https://blog.eleuther.ai/
- https://lilianweng.github.io/
- https://oobabooga.github.io/blog/
- https://kipp.ly/
- https://mlu-explain.github.io/
- https://yaofu.notion.site/Yao-Fu-s-Blog-b536c3d6912149a395931f1e871370db

Прикладные курсы 👴
- https://github.com/yandexdataschool/nlp_course
- https://github.com/DanAnastasyev/DeepNLP-Course
(Я давно не проходил вообще никакие курсы, если есть что-то новое и хорошее - пишите!)

Каналы 🚫
- https://t.me/gonzo_ML
- https://t.me/izolenta_mebiusa
- https://t.me/tech_priestess
- https://t.me/rybolos_channel
- https://t.me/j_links
- https://t.me/lovedeathtransformers
- https://t.me/seeallochnaya
- https://t.me/doomgrad
- https://t.me/nadlskom
- https://t.me/dlinnlp
(Забыл добавить вас? Напишите в личку, список составлялся по тем каналам, что я сам читаю)

Чаты 😁
- https://t.me/betterdatacommunity
- https://t.me/natural_language_processing
- https://t.me/LLM_RNN_RWKV
- https://t.me/ldt_chat

Основные статьи 😘
- Word2Vec: Mikolov et al., Efficient Estimation of Word Representations in Vector Space https://arxiv.org/pdf/1301.3781.pdf
- FastText: Bojanowski et al., Enriching Word Vectors with Subword Information https://arxiv.org/pdf/1607.04606.pdf
- Attention: Bahdanau et al., Neural Machine Translation by Jointly Learning to Align and Translate https://arxiv.org/abs/1409.0473
- Transformers: Vaswani et al., Attention Is All You Need https://arxiv.org/abs/1706.03762
- BERT: Devlin et al., BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding https://arxiv.org/abs/1810.0480
- GPT-2, Radford et al., Language Models are Unsupervised Multitask Learners https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
- GPT-3, Brown et al, Language Models are Few-Shot Learners https://arxiv.org/abs/2005.14165
- LaBSE, Feng et al., Language-agnostic BERT Sentence Embedding https://arxiv.org/abs/2007.01852
- CLIP, Radford et al., Learning Transferable Visual Models From Natural Language Supervision https://arxiv.org/abs/2103.00020
- RoPE, Su et al., RoFormer: Enhanced Transformer with Rotary Position Embedding https://arxiv.org/abs/2104.09864
- LoRA, Hu et al., LoRA: Low-Rank Adaptation of Large Language Models https://arxiv.org/abs/2106.09685
- InstructGPT, Ouyang et al., Training language models to follow instructions with human feedback https://arxiv.org/abs/2203.02155
- Scaling laws, Hoffmann et al., Training Compute-Optimal Large Language Models https://arxiv.org/abs/2203.15556
- FlashAttention, Dao et al., FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness https://arxiv.org/abs/2205.14135
- NLLB, NLLB team, No Language Left Behind: Scaling Human-Centered Machine Translation https://arxiv.org/abs/2207.04672
- Q8, Dettmers et al., LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale https://arxiv.org/abs/2208.07339
- Self-instruct, Wang et al., Self-Instruct: Aligning Language Models with Self-Generated Instructions https://arxiv.org/abs/2212.10560
- Alpaca, Taori et al., Alpaca: A Strong, Replicable Instruction-Following Model https://crfm.stanford.edu/2023/03/13/alpaca.html
- LLaMA, Touvron, et al., LLaMA: Open and Efficient Foundation Language Models https://arxiv.org/abs/2302.13971