https://bearbearyu1223.github.io/posts/food-qna-on-server-llm/ 2023-07-31T00:00:00-07:00 https://bearbearyu1223.github.io/posts/food-qna-on-device-llm/ 2023-08-14T00:00:00-07:00 https://bearbearyu1223.github.io/posts/conversation-sim/ 2023-09-07T00:00:00-07:00 https://bearbearyu1223.github.io/posts/assistant-api-playground/ 2023-11-21T00:00:00-08:00 https://bearbearyu1223.github.io/posts/PEFT-summarization/ 2024-01-01T00:00:00-08:00 https://bearbearyu1223.github.io/posts/cs336-note-get-started/ 2025-07-20T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-note-simple-bpe/ 2025-07-22T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-note-train-bpe-tinystories/ 2025-07-26T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-gpt2-regex-for-pretokenization-explaind/ 2025-08-10T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-build-a-transformer-language-model/ 2025-09-13T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-transformer-architecture-overview/ 2025-09-17T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-understand-computation-cost-of-transformer-model/ 2025-09-28T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-training-a-transformer-lm-part-1/ 2025-10-05T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-implement-softmax-log_softmax-cross_entropy/ 2025-10-19T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-building-a-complete-training-loop/ 2025-11-02T00:00:00-07:00 https://bearbearyu1223.github.io/posts/cs336-the-complete-experiment-for-tinystories-transformer/ 2025-11-16T00:00:00-08:00 https://bearbearyu1223.github.io/posts/cs336-local-to-cloud-training/ 2026-01-11T00:00:00-08:00 https://bearbearyu1223.github.io/posts/cs336-sft-qwen3-for-math-reasoning/ 2026-01-19T00:00:00-08:00 https://bearbearyu1223.github.io/posts/cs336-reinforcement-learning-for-language-model/ 2026-01-25T00:00:00-08:00 https://bearbearyu1223.github.io/posts/grpo-math-reasoning-lambda-cloud/ 2026-02-08T00:00:00-08:00 https://bearbearyu1223.github.io/posts/mcp-claude-skills-social-media-agent/ 2026-03-28T01:00:00-07:00 https://bearbearyu1223.github.io/categories/ 2026-03-28T20:06:45-07:00 https://bearbearyu1223.github.io/tags/ 2026-03-28T20:06:45-07:00 https://bearbearyu1223.github.io/archives/ 2026-03-28T20:06:45-07:00 https://bearbearyu1223.github.io/about/ 2026-03-28T20:06:45-07:00 https://bearbearyu1223.github.io/ https://bearbearyu1223.github.io/tags/rag/ https://bearbearyu1223.github.io/tags/chatbot/ https://bearbearyu1223.github.io/tags/openai/ https://bearbearyu1223.github.io/tags/embeddings/ https://bearbearyu1223.github.io/tags/vector-database/ https://bearbearyu1223.github.io/tags/langchain/ https://bearbearyu1223.github.io/tags/streamlit/ https://bearbearyu1223.github.io/tags/llama2/ https://bearbearyu1223.github.io/tags/on-device/ https://bearbearyu1223.github.io/tags/faiss/ https://bearbearyu1223.github.io/tags/quantization/ https://bearbearyu1223.github.io/tags/apple-silicon/ https://bearbearyu1223.github.io/tags/llm-agents/ https://bearbearyu1223.github.io/tags/conversation-simulation/ https://bearbearyu1223.github.io/tags/multi-agent/ https://bearbearyu1223.github.io/tags/assistant-api/ https://bearbearyu1223.github.io/tags/text-to-speech/ https://bearbearyu1223.github.io/tags/image-generation/ https://bearbearyu1223.github.io/tags/peft/ https://bearbearyu1223.github.io/tags/qlora/ https://bearbearyu1223.github.io/tags/lora/ https://bearbearyu1223.github.io/tags/fine-tuning/ https://bearbearyu1223.github.io/tags/falcon-7b/ https://bearbearyu1223.github.io/tags/summarization/ https://bearbearyu1223.github.io/tags/llm-evaluation/ https://bearbearyu1223.github.io/tags/cs336/ https://bearbearyu1223.github.io/tags/setup/ https://bearbearyu1223.github.io/tags/development-environment/ https://bearbearyu1223.github.io/tags/python/ https://bearbearyu1223.github.io/tags/uv/ https://bearbearyu1223.github.io/tags/bpe/ https://bearbearyu1223.github.io/tags/tokenization/ https://bearbearyu1223.github.io/tags/unicode/ https://bearbearyu1223.github.io/tags/utf-8/ https://bearbearyu1223.github.io/tags/byte-pair-encoding/ https://bearbearyu1223.github.io/tags/tinystories/ https://bearbearyu1223.github.io/tags/compression/ https://bearbearyu1223.github.io/tags/pretokenization/ https://bearbearyu1223.github.io/tags/regex/ https://bearbearyu1223.github.io/tags/gpt-2/ https://bearbearyu1223.github.io/tags/multilingual/ https://bearbearyu1223.github.io/tags/transformer/ https://bearbearyu1223.github.io/tags/attention/ https://bearbearyu1223.github.io/tags/pytorch/ https://bearbearyu1223.github.io/tags/language-model/ https://bearbearyu1223.github.io/tags/swiglu/ https://bearbearyu1223.github.io/tags/rope/ https://bearbearyu1223.github.io/tags/encoder-decoder/ https://bearbearyu1223.github.io/tags/gpt/ https://bearbearyu1223.github.io/tags/bert/ https://bearbearyu1223.github.io/tags/t5/ https://bearbearyu1223.github.io/tags/llama/ https://bearbearyu1223.github.io/tags/architecture/ https://bearbearyu1223.github.io/tags/flops/ https://bearbearyu1223.github.io/tags/computation/ https://bearbearyu1223.github.io/tags/scaling-laws/ https://bearbearyu1223.github.io/tags/optimization/ https://bearbearyu1223.github.io/tags/cross-entropy/ https://bearbearyu1223.github.io/tags/perplexity/ https://bearbearyu1223.github.io/tags/adamw/ https://bearbearyu1223.github.io/tags/optimizer/ https://bearbearyu1223.github.io/tags/memory/ https://bearbearyu1223.github.io/tags/training/ https://bearbearyu1223.github.io/tags/softmax/ https://bearbearyu1223.github.io/tags/numerical-stability/ https://bearbearyu1223.github.io/tags/training-loop/ https://bearbearyu1223.github.io/tags/learning-rate/ https://bearbearyu1223.github.io/tags/checkpointing/ https://bearbearyu1223.github.io/tags/data-loading/ https://bearbearyu1223.github.io/tags/end-to-end/ https://bearbearyu1223.github.io/tags/text-generation/ https://bearbearyu1223.github.io/tags/sft/ https://bearbearyu1223.github.io/tags/cloud-training/ https://bearbearyu1223.github.io/tags/colab/ https://bearbearyu1223.github.io/tags/lambda-labs/ https://bearbearyu1223.github.io/tags/cuda/ https://bearbearyu1223.github.io/tags/qwen/ https://bearbearyu1223.github.io/tags/math-reasoning/ https://bearbearyu1223.github.io/tags/reinforcement-learning/ https://bearbearyu1223.github.io/tags/policy-gradient/ https://bearbearyu1223.github.io/tags/rlhf/ https://bearbearyu1223.github.io/tags/grpo/ https://bearbearyu1223.github.io/tags/ppo/ https://bearbearyu1223.github.io/tags/lambda-cloud/ https://bearbearyu1223.github.io/tags/h100/ https://bearbearyu1223.github.io/tags/mcp/ https://bearbearyu1223.github.io/tags/claude/ https://bearbearyu1223.github.io/tags/xiaohongshu/ https://bearbearyu1223.github.io/tags/content-creator/ https://bearbearyu1223.github.io/tags/agent/ https://bearbearyu1223.github.io/tags/claude-skills/ https://bearbearyu1223.github.io/tags/claude-code/ https://bearbearyu1223.github.io/categories/genai-projects/ https://bearbearyu1223.github.io/categories/rag/ https://bearbearyu1223.github.io/categories/on-device-llm/ https://bearbearyu1223.github.io/categories/multi-agent/ https://bearbearyu1223.github.io/categories/assistants/ https://bearbearyu1223.github.io/categories/fine-tuning/ https://bearbearyu1223.github.io/categories/cs336/ https://bearbearyu1223.github.io/categories/getting-started/ https://bearbearyu1223.github.io/categories/tokenization/ https://bearbearyu1223.github.io/categories/transformers/ https://bearbearyu1223.github.io/categories/training/ https://bearbearyu1223.github.io/categories/infrastructure/ https://bearbearyu1223.github.io/categories/reinforcement-learning/ https://bearbearyu1223.github.io/categories/mcp/ https://bearbearyu1223.github.io/categories/agent/ https://bearbearyu1223.github.io/page2/ https://bearbearyu1223.github.io/page3/