https://llm-primer.pages.dev/https://llm-primer.pages.dev/blog/why-llm-primer/https://llm-primer.pages.dev/en/https://llm-primer.pages.dev/en/blog/why-llm-primer/https://llm-primer.pages.dev/en/foundations/attention/https://llm-primer.pages.dev/en/foundations/embeddings/https://llm-primer.pages.dev/en/foundations/positional-encoding/https://llm-primer.pages.dev/en/foundations/sampling-and-decoding/https://llm-primer.pages.dev/en/foundations/tokenization/https://llm-primer.pages.dev/en/foundations/transformer-architecture/https://llm-primer.pages.dev/en/foundations/why-llm-emerges/https://llm-primer.pages.dev/en/glossary/https://llm-primer.pages.dev/en/papers/https://llm-primer.pages.dev/en/papers/abdin2024-phi3/https://llm-primer.pages.dev/en/papers/ai2024-yi/https://llm-primer.pages.dev/en/papers/ainslie2023-gqa/https://llm-primer.pages.dev/en/papers/alayrac2022-flamingo/https://llm-primer.pages.dev/en/papers/anthropic2024-mcp/https://llm-primer.pages.dev/en/papers/azar2023-ipo/https://llm-primer.pages.dev/en/papers/bahdanau2014-attention/https://llm-primer.pages.dev/en/papers/bai2022-constitutional-ai/https://llm-primer.pages.dev/en/papers/bai2022-hh/https://llm-primer.pages.dev/en/papers/bai2023-qwen/https://llm-primer.pages.dev/en/papers/borgeaud2022-retro/https://llm-primer.pages.dev/en/papers/brown2020-gpt3/https://llm-primer.pages.dev/en/papers/chen2021-humaneval/https://llm-primer.pages.dev/en/papers/chen2023-longlora/https://llm-primer.pages.dev/en/papers/chen2023-spec-sampling/https://llm-primer.pages.dev/en/papers/chowdhery2022-palm/https://llm-primer.pages.dev/en/papers/christiano2017-rlhf/https://llm-primer.pages.dev/en/papers/clark2020-electra/https://llm-primer.pages.dev/en/papers/dao2022-flashattention/https://llm-primer.pages.dev/en/papers/dao2023-flashattention2/https://llm-primer.pages.dev/en/papers/deepseek2024-v2/https://llm-primer.pages.dev/en/papers/deepseek2024-v3/https://llm-primer.pages.dev/en/papers/deepseek2025-r1/https://llm-primer.pages.dev/en/papers/dettmers2022-llmint8/https://llm-primer.pages.dev/en/papers/dettmers2023-qlora/https://llm-primer.pages.dev/en/papers/devlin2018-bert/https://llm-primer.pages.dev/en/papers/du2021-glam/https://llm-primer.pages.dev/en/papers/dubey2024-llama3/https://llm-primer.pages.dev/en/papers/fedus2021-switch/https://llm-primer.pages.dev/en/papers/frantar2022-gptq/https://llm-primer.pages.dev/en/papers/gao2022-hyde/https://llm-primer.pages.dev/en/papers/gemini2023-team/https://llm-primer.pages.dev/en/papers/gunasekar2023-phi1/https://llm-primer.pages.dev/en/papers/hendrycks2020-mmlu/https://llm-primer.pages.dev/en/papers/hoffmann2022-chinchilla/https://llm-primer.pages.dev/en/papers/howard2018-ulmfit/https://llm-primer.pages.dev/en/papers/hu2021-lora/https://llm-primer.pages.dev/en/papers/jiang2023-mistral7b/https://llm-primer.pages.dev/en/papers/jiang2024-mixtral/https://llm-primer.pages.dev/en/papers/jimenez2024-swebench/https://llm-primer.pages.dev/en/papers/kalchbrenner2016-bytenet/https://llm-primer.pages.dev/en/papers/kaplan2020-scaling/https://llm-primer.pages.dev/en/papers/karpukhin2020-dpr/https://llm-primer.pages.dev/en/papers/kim2014-textcnn/https://llm-primer.pages.dev/en/papers/kojima2022-zeroshot-cot/https://llm-primer.pages.dev/en/papers/kwon2023-vllm/https://llm-primer.pages.dev/en/papers/lee2023-rlaif/https://llm-primer.pages.dev/en/papers/leviathan2023-spec-decoding/https://llm-primer.pages.dev/en/papers/lewis2020-rag/https://llm-primer.pages.dev/en/papers/liang2022-helm/https://llm-primer.pages.dev/en/papers/lin2023-awq/https://llm-primer.pages.dev/en/papers/liu2019-roberta/https://llm-primer.pages.dev/en/papers/liu2023-llava/https://llm-primer.pages.dev/en/papers/luong2015-attention/https://llm-primer.pages.dev/en/papers/mikolov2013-skipgram-negsampling/https://llm-primer.pages.dev/en/papers/mikolov2013-word2vec/https://llm-primer.pages.dev/en/papers/openai2023-gpt4/https://llm-primer.pages.dev/en/papers/openai2023-gpt4v/https://llm-primer.pages.dev/en/papers/openai2024-o1-systemcard/https://llm-primer.pages.dev/en/papers/ouyang2022-instructgpt/https://llm-primer.pages.dev/en/papers/peng2023-yarn/https://llm-primer.pages.dev/en/papers/perez2022-redteaming/https://llm-primer.pages.dev/en/papers/peters2018-elmo/https://llm-primer.pages.dev/en/papers/press2021-alibi/https://llm-primer.pages.dev/en/papers/qwen2024-qwen25/https://llm-primer.pages.dev/en/papers/radford2018-gpt1/https://llm-primer.pages.dev/en/papers/radford2019-gpt2/https://llm-primer.pages.dev/en/papers/radford2021-clip/https://llm-primer.pages.dev/en/papers/rafailov2023-dpo/https://llm-primer.pages.dev/en/papers/raffel2020-t5/https://llm-primer.pages.dev/en/papers/schick2023-toolformer/https://llm-primer.pages.dev/en/papers/shah2024-flashattention3/https://llm-primer.pages.dev/en/papers/shazeer2019-mqa/https://llm-primer.pages.dev/en/papers/shinn2023-reflexion/https://llm-primer.pages.dev/en/papers/snell2024-test-time-compute/https://llm-primer.pages.dev/en/papers/stiennon2020-summarize/https://llm-primer.pages.dev/en/papers/su2021-rope/https://llm-primer.pages.dev/en/papers/sutskever2014-seq2seq/https://llm-primer.pages.dev/en/papers/taori2023-alpaca/https://llm-primer.pages.dev/en/papers/touvron2023-llama/https://llm-primer.pages.dev/en/papers/touvron2023-llama2/https://llm-primer.pages.dev/en/papers/vaswani2017-attention/https://llm-primer.pages.dev/en/papers/wang2022-self-consistency/https://llm-primer.pages.dev/en/papers/wang2022-self-instruct/https://llm-primer.pages.dev/en/papers/wei2022-cot/https://llm-primer.pages.dev/en/papers/wei2023-jailbroken/https://llm-primer.pages.dev/en/papers/xiao2022-smoothquant/https://llm-primer.pages.dev/en/papers/yang2019-xlnet/https://llm-primer.pages.dev/en/papers/yang2024-sweagent/https://llm-primer.pages.dev/en/papers/yao2022-react/https://llm-primer.pages.dev/en/papers/yao2023-tot/https://llm-primer.pages.dev/en/papers/zeng2022-glm130b/https://llm-primer.pages.dev/en/papers/zheng2023-mtbench/https://llm-primer.pages.dev/en/papers/zhou2022-least-to-most/https://llm-primer.pages.dev/en/papers/zou2023-universal-attack/https://llm-primer.pages.dev/foundations/attention/https://llm-primer.pages.dev/foundations/embeddings/https://llm-primer.pages.dev/foundations/positional-encoding/https://llm-primer.pages.dev/foundations/sampling-and-decoding/https://llm-primer.pages.dev/foundations/tokenization/https://llm-primer.pages.dev/foundations/transformer-architecture/https://llm-primer.pages.dev/foundations/why-llm-emerges/https://llm-primer.pages.dev/glossary/https://llm-primer.pages.dev/papers/https://llm-primer.pages.dev/papers/abdin2024-phi3/https://llm-primer.pages.dev/papers/ai2024-yi/https://llm-primer.pages.dev/papers/ainslie2023-gqa/https://llm-primer.pages.dev/papers/alayrac2022-flamingo/https://llm-primer.pages.dev/papers/anthropic2024-mcp/https://llm-primer.pages.dev/papers/azar2023-ipo/https://llm-primer.pages.dev/papers/bahdanau2014-attention/https://llm-primer.pages.dev/papers/bai2022-constitutional-ai/https://llm-primer.pages.dev/papers/bai2022-hh/https://llm-primer.pages.dev/papers/bai2023-qwen/https://llm-primer.pages.dev/papers/borgeaud2022-retro/https://llm-primer.pages.dev/papers/brown2020-gpt3/https://llm-primer.pages.dev/papers/chen2021-humaneval/https://llm-primer.pages.dev/papers/chen2023-longlora/https://llm-primer.pages.dev/papers/chen2023-spec-sampling/https://llm-primer.pages.dev/papers/chowdhery2022-palm/https://llm-primer.pages.dev/papers/christiano2017-rlhf/https://llm-primer.pages.dev/papers/clark2020-electra/https://llm-primer.pages.dev/papers/dao2022-flashattention/https://llm-primer.pages.dev/papers/dao2023-flashattention2/https://llm-primer.pages.dev/papers/deepseek2024-v2/https://llm-primer.pages.dev/papers/deepseek2024-v3/https://llm-primer.pages.dev/papers/deepseek2025-r1/https://llm-primer.pages.dev/papers/dettmers2022-llmint8/https://llm-primer.pages.dev/papers/dettmers2023-qlora/https://llm-primer.pages.dev/papers/devlin2018-bert/https://llm-primer.pages.dev/papers/du2021-glam/https://llm-primer.pages.dev/papers/dubey2024-llama3/https://llm-primer.pages.dev/papers/fedus2021-switch/https://llm-primer.pages.dev/papers/frantar2022-gptq/https://llm-primer.pages.dev/papers/gao2022-hyde/https://llm-primer.pages.dev/papers/gemini2023-team/https://llm-primer.pages.dev/papers/gunasekar2023-phi1/https://llm-primer.pages.dev/papers/hendrycks2020-mmlu/https://llm-primer.pages.dev/papers/hoffmann2022-chinchilla/https://llm-primer.pages.dev/papers/howard2018-ulmfit/https://llm-primer.pages.dev/papers/hu2021-lora/https://llm-primer.pages.dev/papers/jiang2023-mistral7b/https://llm-primer.pages.dev/papers/jiang2024-mixtral/https://llm-primer.pages.dev/papers/jimenez2024-swebench/https://llm-primer.pages.dev/papers/kalchbrenner2016-bytenet/https://llm-primer.pages.dev/papers/kaplan2020-scaling/https://llm-primer.pages.dev/papers/karpukhin2020-dpr/https://llm-primer.pages.dev/papers/kim2014-textcnn/https://llm-primer.pages.dev/papers/kojima2022-zeroshot-cot/https://llm-primer.pages.dev/papers/kwon2023-vllm/https://llm-primer.pages.dev/papers/lee2023-rlaif/https://llm-primer.pages.dev/papers/leviathan2023-spec-decoding/https://llm-primer.pages.dev/papers/lewis2020-rag/https://llm-primer.pages.dev/papers/liang2022-helm/https://llm-primer.pages.dev/papers/lin2023-awq/https://llm-primer.pages.dev/papers/liu2019-roberta/https://llm-primer.pages.dev/papers/liu2023-llava/https://llm-primer.pages.dev/papers/luong2015-attention/https://llm-primer.pages.dev/papers/mikolov2013-skipgram-negsampling/https://llm-primer.pages.dev/papers/mikolov2013-word2vec/https://llm-primer.pages.dev/papers/openai2023-gpt4/https://llm-primer.pages.dev/papers/openai2023-gpt4v/https://llm-primer.pages.dev/papers/openai2024-o1-systemcard/https://llm-primer.pages.dev/papers/ouyang2022-instructgpt/https://llm-primer.pages.dev/papers/peng2023-yarn/https://llm-primer.pages.dev/papers/perez2022-redteaming/https://llm-primer.pages.dev/papers/peters2018-elmo/https://llm-primer.pages.dev/papers/press2021-alibi/https://llm-primer.pages.dev/papers/qwen2024-qwen25/https://llm-primer.pages.dev/papers/radford2018-gpt1/https://llm-primer.pages.dev/papers/radford2019-gpt2/https://llm-primer.pages.dev/papers/radford2021-clip/https://llm-primer.pages.dev/papers/rafailov2023-dpo/https://llm-primer.pages.dev/papers/raffel2020-t5/https://llm-primer.pages.dev/papers/schick2023-toolformer/https://llm-primer.pages.dev/papers/shah2024-flashattention3/https://llm-primer.pages.dev/papers/shazeer2019-mqa/https://llm-primer.pages.dev/papers/shinn2023-reflexion/https://llm-primer.pages.dev/papers/snell2024-test-time-compute/https://llm-primer.pages.dev/papers/stiennon2020-summarize/https://llm-primer.pages.dev/papers/su2021-rope/https://llm-primer.pages.dev/papers/sutskever2014-seq2seq/https://llm-primer.pages.dev/papers/taori2023-alpaca/https://llm-primer.pages.dev/papers/touvron2023-llama/https://llm-primer.pages.dev/papers/touvron2023-llama2/https://llm-primer.pages.dev/papers/vaswani2017-attention/https://llm-primer.pages.dev/papers/wang2022-self-consistency/https://llm-primer.pages.dev/papers/wang2022-self-instruct/https://llm-primer.pages.dev/papers/wei2022-cot/https://llm-primer.pages.dev/papers/wei2023-jailbroken/https://llm-primer.pages.dev/papers/xiao2022-smoothquant/https://llm-primer.pages.dev/papers/yang2019-xlnet/https://llm-primer.pages.dev/papers/yang2024-sweagent/https://llm-primer.pages.dev/papers/yao2022-react/https://llm-primer.pages.dev/papers/yao2023-tot/https://llm-primer.pages.dev/papers/zeng2022-glm130b/https://llm-primer.pages.dev/papers/zheng2023-mtbench/https://llm-primer.pages.dev/papers/zhou2022-least-to-most/https://llm-primer.pages.dev/papers/zou2023-universal-attack/