https://ai.flicky.cc/https://ai.flicky.cc/china/01-ecosystem/https://ai.flicky.cc/china/02-why-efficient/https://ai.flicky.cc/china/03-open-weights/https://ai.flicky.cc/china/04-reading-chinese/https://ai.flicky.cc/china/05-education/https://ai.flicky.cc/china/06-deepseek-v3-reading/https://ai.flicky.cc/china/07-deepseek-r1-reading/https://ai.flicky.cc/china/08-kimi-qwen-glm/https://ai.flicky.cc/china/09-ai-education-china/https://ai.flicky.cc/china/10-learn-like-china/https://ai.flicky.cc/creators/https://ai.flicky.cc/ddd/ddd-1-language/01-why-ddd/https://ai.flicky.cc/ddd/ddd-1-language/02-ubiquitous-language/https://ai.flicky.cc/ddd/ddd-1-language/03-subdomains/https://ai.flicky.cc/ddd/ddd-2-strategic/01-bounded-contexts/https://ai.flicky.cc/ddd/ddd-2-strategic/02-context-mapping/https://ai.flicky.cc/ddd/ddd-2-strategic/03-event-storming/https://ai.flicky.cc/ddd/ddd-3-tactical/01-entities-value-objects/https://ai.flicky.cc/ddd/ddd-3-tactical/02-aggregates/https://ai.flicky.cc/ddd/ddd-3-tactical/03-events-services-factories/https://ai.flicky.cc/ddd/ddd-3-tactical/04-repositories-architecture/https://ai.flicky.cc/ddd/ddd-4-practice/01-cqrs-event-sourcing/https://ai.flicky.cc/ddd/ddd-4-practice/02-integration/https://ai.flicky.cc/ddd/ddd-4-practice/03-legacy/https://ai.flicky.cc/ddd/ddd-4-practice/04-ddd-and-ai/https://ai.flicky.cc/glossary/https://ai.flicky.cc/lab/https://ai.flicky.cc/library/https://ai.flicky.cc/mistakes/https://ai.flicky.cc/programs/https://ai.flicky.cc/progress/https://ai.flicky.cc/review/https://ai.flicky.cc/sdd/sdd-1-idea/01-what-is-sdd/https://ai.flicky.cc/sdd/sdd-1-idea/02-agents-and-context/https://ai.flicky.cc/sdd/sdd-2-specs/01-requirements/https://ai.flicky.cc/sdd/sdd-2-specs/02-design-and-plan/https://ai.flicky.cc/sdd/sdd-2-specs/03-tasks-and-constitution/https://ai.flicky.cc/sdd/sdd-3-tools/01-spec-kit/https://ai.flicky.cc/sdd/sdd-3-tools/02-openspec/https://ai.flicky.cc/sdd/sdd-3-tools/03-landscape/https://ai.flicky.cc/sdd/sdd-4-practice/01-workflow/https://ai.flicky.cc/sdd/sdd-4-practice/02-verification/https://ai.flicky.cc/sdd/sdd-4-practice/03-pitfalls/https://ai.flicky.cc/sdd/sdd-4-practice/04-capstone/https://ai.flicky.cc/stage-0/0-0-zero/01-what-is-ai/https://ai.flicky.cc/stage-0/0-0-zero/02-how-computers-run-code/https://ai.flicky.cc/stage-0/0-0-zero/03-how-to-learn-coding/https://ai.flicky.cc/stage-0/0-1-environment/01-terminal-git/https://ai.flicky.cc/stage-0/0-1-environment/02-python-env/https://ai.flicky.cc/stage-0/0-1-environment/03-how-homework-works/https://ai.flicky.cc/stage-0/0-2-python/00-first-program/https://ai.flicky.cc/stage-0/0-2-python/01-basics/https://ai.flicky.cc/stage-0/0-2-python/02-functions/https://ai.flicky.cc/stage-0/0-2-python/03-classes/https://ai.flicky.cc/stage-0/0-2-python/04-files-modules/https://ai.flicky.cc/stage-0/0-2-python/05-errors-debugging/https://ai.flicky.cc/stage-0/0-2-python/06-mini-projects/https://ai.flicky.cc/stage-0/0-3-numpy/01-arrays/https://ai.flicky.cc/stage-0/0-3-numpy/02-broadcasting/https://ai.flicky.cc/stage-0/0-3-numpy/03-random-plots/https://ai.flicky.cc/stage-1/1-0-school-math/01-functions-graphs/https://ai.flicky.cc/stage-1/1-0-school-math/02-powers-logs/https://ai.flicky.cc/stage-1/1-0-school-math/03-reading-formulas/https://ai.flicky.cc/stage-1/1-0-school-math/04-trigonometry/https://ai.flicky.cc/stage-1/1-0-school-math/05-sets-combinatorics/https://ai.flicky.cc/stage-1/1-1-linear-algebra/01-vectors/https://ai.flicky.cc/stage-1/1-1-linear-algebra/02-matrices/https://ai.flicky.cc/stage-1/1-1-linear-algebra/03-rank-decompositions/https://ai.flicky.cc/stage-1/1-2-calculus/01-derivatives/https://ai.flicky.cc/stage-1/1-2-calculus/02-chain-rule/https://ai.flicky.cc/stage-1/1-2-calculus/03-gradients/https://ai.flicky.cc/stage-1/1-3-probability/01-probability/https://ai.flicky.cc/stage-1/1-3-probability/02-mle-softmax/https://ai.flicky.cc/stage-1/1-3-probability/03-entropy-kl/https://ai.flicky.cc/stage-1/1-3-probability/04-statistics-for-experiments/https://ai.flicky.cc/stage-1/1-4-optimization/01-gradient-descent/https://ai.flicky.cc/stage-1/1-4-optimization/02-momentum-adam/https://ai.flicky.cc/stage-2/2-1-ml-basics/01-what-is-ml/https://ai.flicky.cc/stage-2/2-1-ml-basics/02-generalization/https://ai.flicky.cc/stage-2/2-2-linear-models/01-linear-regression/https://ai.flicky.cc/stage-2/2-2-linear-models/02-logistic-regression/https://ai.flicky.cc/stage-2/2-2-linear-models/03-metrics/https://ai.flicky.cc/stage-2/2-3-classic-ml/01-trees-knn/https://ai.flicky.cc/stage-2/2-3-classic-ml/02-unsupervised/https://ai.flicky.cc/stage-2/2-4-tabular-practice/01-pandas/https://ai.flicky.cc/stage-2/2-4-tabular-practice/02-eda-visualization/https://ai.flicky.cc/stage-2/2-4-tabular-practice/03-gradient-boosting/https://ai.flicky.cc/stage-2/2-4-tabular-practice/04-tabular-pipeline/https://ai.flicky.cc/stage-3/3-1-neural-nets/01-neuron-mlp/https://ai.flicky.cc/stage-3/3-1-neural-nets/02-forward-backward/https://ai.flicky.cc/stage-3/3-2-micrograd/01-value-graph/https://ai.flicky.cc/stage-3/3-2-micrograd/02-backward/https://ai.flicky.cc/stage-3/3-2-micrograd/03-train-mlp/https://ai.flicky.cc/stage-3/3-3-pytorch/01-tensors-autograd/https://ai.flicky.cc/stage-3/3-3-pytorch/02-nn-module/https://ai.flicky.cc/stage-3/3-3-pytorch/03-debugging/https://ai.flicky.cc/stage-3/3-4-deep-training/01-init-normalization/https://ai.flicky.cc/stage-3/3-4-deep-training/02-residual-dropout/https://ai.flicky.cc/stage-3/3-4-deep-training/03-cnn-rnn/https://ai.flicky.cc/stage-3/3-5-computer-vision/01-convolution-from-scratch/https://ai.flicky.cc/stage-3/3-5-computer-vision/02-cnn-practice-transfer/https://ai.flicky.cc/stage-4/4-1-language-modeling/01-what-is-lm/https://ai.flicky.cc/stage-4/4-1-language-modeling/02-bigram-model/https://ai.flicky.cc/stage-4/4-1-language-modeling/03-sampling/https://ai.flicky.cc/stage-4/4-1-language-modeling/04-mlp-language-model/https://ai.flicky.cc/stage-4/4-1-language-modeling/05-rnn-lstm-language-model/https://ai.flicky.cc/stage-4/4-2-tokenization/01-why-tokens/https://ai.flicky.cc/stage-4/4-2-tokenization/02-bpe/https://ai.flicky.cc/stage-4/4-2-tokenization/03-tokenizers-in-practice/https://ai.flicky.cc/stage-4/4-3-embeddings/01-word-vectors/https://ai.flicky.cc/stage-4/4-3-embeddings/02-train-word2vec/https://ai.flicky.cc/stage-4/4-4-attention/01-attention-intuition/https://ai.flicky.cc/stage-4/4-4-attention/02-self-attention/https://ai.flicky.cc/stage-4/4-4-attention/03-multi-head/https://ai.flicky.cc/stage-4/4-5-transformer/01-transformer-block/https://ai.flicky.cc/stage-4/4-5-transformer/02-positional-encoding/https://ai.flicky.cc/stage-4/4-5-transformer/03-modern-block/https://ai.flicky.cc/stage-4/4-5-transformer/04-bert-and-hf/https://ai.flicky.cc/stage-4/4-6-gpt-from-scratch/01-micro-gpt/https://ai.flicky.cc/stage-4/4-6-gpt-from-scratch/02-nanogpt-pytorch/https://ai.flicky.cc/stage-4/4-6-gpt-from-scratch/03-training-loop/https://ai.flicky.cc/stage-4/4-6-gpt-from-scratch/04-kv-cache/https://ai.flicky.cc/stage-4/4-6-gpt-from-scratch/05-llm-toolbox/https://ai.flicky.cc/stage-5/5-1-scaling/01-scaling-laws/https://ai.flicky.cc/stage-5/5-1-scaling/02-pretraining-data/https://ai.flicky.cc/stage-5/5-2-efficient-attention/01-mqa-gqa/https://ai.flicky.cc/stage-5/5-2-efficient-attention/02-mla/https://ai.flicky.cc/stage-5/5-3-moe/01-moe-basics/https://ai.flicky.cc/stage-5/5-3-moe/02-deepseekmoe/https://ai.flicky.cc/stage-5/5-4-efficient-training/01-mixed-precision/https://ai.flicky.cc/stage-5/5-4-efficient-training/02-mtp/https://ai.flicky.cc/stage-5/5-4-efficient-training/03-distributed/https://ai.flicky.cc/stage-5/5-4-efficient-training/04-optimizers-stability/https://ai.flicky.cc/stage-5/5-5-long-context/01-rope-scaling/https://ai.flicky.cc/stage-5/5-5-long-context/02-sparse-attention/https://ai.flicky.cc/stage-5/5-5-long-context/03-linear-attention/https://ai.flicky.cc/stage-5/5-6-minimind/01-minimind-overview/https://ai.flicky.cc/stage-5/5-6-minimind/02-pretrain-project/https://ai.flicky.cc/stage-5/5-7-gpu-internals/01-gpu-architecture-profiling/https://ai.flicky.cc/stage-5/5-7-gpu-internals/02-flashattention/https://ai.flicky.cc/stage-5/5-7-gpu-internals/03-triton-kernels/https://ai.flicky.cc/stage-5/5-7-gpu-internals/04-multi-gpu-practice/https://ai.flicky.cc/stage-6/6-0-rl-foundations/01-mdp-bellman/https://ai.flicky.cc/stage-6/6-0-rl-foundations/02-td-q-learning/https://ai.flicky.cc/stage-6/6-0-rl-foundations/03-actor-critic-gae-ppo/https://ai.flicky.cc/stage-6/6-1-sft/01-base-vs-chat/https://ai.flicky.cc/stage-6/6-1-sft/02-sft/https://ai.flicky.cc/stage-6/6-2-peft/01-lora/https://ai.flicky.cc/stage-6/6-2-peft/02-finetune-practice/https://ai.flicky.cc/stage-6/6-3-preferences/01-rl-basics/https://ai.flicky.cc/stage-6/6-3-preferences/02-rlhf-ppo/https://ai.flicky.cc/stage-6/6-3-preferences/03-dpo/https://ai.flicky.cc/stage-6/6-4-reasoning/01-grpo/https://ai.flicky.cc/stage-6/6-4-reasoning/02-r1-zero/https://ai.flicky.cc/stage-6/6-4-reasoning/03-grpo-variants/https://ai.flicky.cc/stage-6/6-4-reasoning/04-distillation-thinking/https://ai.flicky.cc/stage-6/6-4-reasoning/05-grpo-practice/https://ai.flicky.cc/stage-7/7-1-inference/01-prefill-decode/https://ai.flicky.cc/stage-7/7-1-inference/02-serving/https://ai.flicky.cc/stage-7/7-2-quantization/01-quantization/https://ai.flicky.cc/stage-7/7-2-quantization/02-local-llm/https://ai.flicky.cc/stage-7/7-3-evaluation/01-benchmarks/https://ai.flicky.cc/stage-7/7-3-evaluation/02-llm-as-judge/https://ai.flicky.cc/stage-8/8-1-llm-api/01-api-basics/https://ai.flicky.cc/stage-8/8-1-llm-api/02-prompting/https://ai.flicky.cc/stage-8/8-2-rag/01-rag-basics/https://ai.flicky.cc/stage-8/8-2-rag/02-rag-advanced/https://ai.flicky.cc/stage-8/8-3-agents/01-agent-loop/https://ai.flicky.cc/stage-8/8-3-agents/02-tools-mcp/https://ai.flicky.cc/stage-8/8-3-agents/03-planning-memory/https://ai.flicky.cc/stage-8/8-3-agents/04-agentic-rl-safety/https://ai.flicky.cc/stage-8/8-4-production/01-prompt-engineering-discipline/https://ai.flicky.cc/stage-8/8-4-production/02-evals-observability/https://ai.flicky.cc/stage-8/8-4-production/03-deploy-llm-service/https://ai.flicky.cc/stage-8/8-5-orchestration/01-landscape/https://ai.flicky.cc/stage-8/8-5-orchestration/02-langgraph/https://ai.flicky.cc/stage-8/8-5-orchestration/03-agent-sdks/https://ai.flicky.cc/stage-8/8-5-orchestration/04-multi-agent-production/https://ai.flicky.cc/stage-8/8-5-orchestration/05-capstone-practicum/https://ai.flicky.cc/stage-9/9-1-multimodal/01-vision-language/https://ai.flicky.cc/stage-9/9-1-multimodal/02-diffusion/https://ai.flicky.cc/stage-9/9-1-multimodal/03-autoencoders-vae-vq/https://ai.flicky.cc/stage-9/9-1-multimodal/04-flow-matching/https://ai.flicky.cc/stage-9/9-1-multimodal/05-speech/https://ai.flicky.cc/stage-9/9-2-frontier/01-frontier-2026/https://ai.flicky.cc/stage-9/9-2-frontier/02-reading-papers/https://ai.flicky.cc/stage-9/9-3-interpretability-safety/01-mech-interp/https://ai.flicky.cc/stage-9/9-3-interpretability-safety/02-superposition-sae/https://ai.flicky.cc/stage-9/9-3-interpretability-safety/03-alignment/https://ai.flicky.cc/stage-9/9-3-interpretability-safety/04-safety-evals-redteaming/https://ai.flicky.cc/stage-9/9-3-interpretability-safety/05-ethics-law/https://ai.flicky.cc/stage-10/10-1-capstone/01-capstone-plan/https://ai.flicky.cc/stage-10/10-1-capstone/02-capstone-report/https://ai.flicky.cc/stage-11/11-1-real-work/01-messy-data/https://ai.flicky.cc/stage-11/11-1-real-work/02-legacy-code/https://ai.flicky.cc/stage-11/11-1-real-work/03-experiments/https://ai.flicky.cc/stage-11/11-1-real-work/04-production-incidents/https://ai.flicky.cc/stage-11/11-1-real-work/05-cost-and-tradeoffs/https://ai.flicky.cc/stage-11/11-2-system-design/01-design-framework/https://ai.flicky.cc/stage-11/11-2-system-design/02-case-rag-assistant/https://ai.flicky.cc/stage-11/11-2-system-design/03-case-recsys/https://ai.flicky.cc/stage-11/11-2-system-design/04-case-moderation-search/https://ai.flicky.cc/stage-11/11-2-system-design/05-case-llm-platform/https://ai.flicky.cc/stage-11/11-3-interviews/01-hiring-process/https://ai.flicky.cc/stage-11/11-3-interviews/02-ml-theory-questions/https://ai.flicky.cc/stage-11/11-3-interviews/03-llm-questions/https://ai.flicky.cc/stage-11/11-3-interviews/04-ml-coding/https://ai.flicky.cc/stage-11/11-3-interviews/05-algorithms/https://ai.flicky.cc/stage-11/11-3-interviews/06-resume-portfolio/https://ai.flicky.cc/stage-11/11-4-growth/01-reproduce-papers/https://ai.flicky.cc/stage-11/11-4-growth/02-open-source/https://ai.flicky.cc/stage-11/11-4-growth/03-competitions/https://ai.flicky.cc/stage-11/11-4-growth/04-feedback-community/https://ai.flicky.cc/stage-11/11-4-growth/05-career-plan/https://ai.flicky.cc/start/about/https://ai.flicky.cc/start/diagnostic/https://ai.flicky.cc/start/hardware/https://ai.flicky.cc/start/how-to-learn/https://ai.flicky.cc/start/setup/https://ai.flicky.cc/translations/https://ai.flicky.cc/translations/anthropic/api-fundamentals/https://ai.flicky.cc/translations/anthropic/circuit-tracer-neuronpedia/https://ai.flicky.cc/translations/anthropic/circuits-biology/https://ai.flicky.cc/translations/anthropic/circuits-framework/https://ai.flicky.cc/translations/anthropic/circuits-induction-heads/https://ai.flicky.cc/translations/anthropic/circuits-monosemanticity/https://ai.flicky.cc/translations/anthropic/circuits-superposition/https://ai.flicky.cc/translations/anthropic/circuits-tracing/https://ai.flicky.cc/translations/anthropic/claude-academy/https://ai.flicky.cc/translations/anthropic/cookbook-building-evals/https://ai.flicky.cc/translations/anthropic/cookbook-customer-service-agent/https://ai.flicky.cc/translations/anthropic/cookbook-rag/https://ai.flicky.cc/translations/anthropic/cookbooks/https://ai.flicky.cc/translations/anthropic/engineering-agents-and-tools/https://ai.flicky.cc/translations/anthropic/engineering-context-and-multiagent/https://ai.flicky.cc/translations/anthropic/engineering-retrieval-and-evals/https://ai.flicky.cc/translations/anthropic/prompt-evaluations-1-basics/https://ai.flicky.cc/translations/anthropic/prompt-evaluations-2-promptfoo/https://ai.flicky.cc/translations/anthropic/prompt-tutorial-1-basics/https://ai.flicky.cc/translations/anthropic/prompt-tutorial-2-intermediate/https://ai.flicky.cc/translations/anthropic/prompt-tutorial-3-advanced/https://ai.flicky.cc/translations/anthropic/real-world-prompting/https://ai.flicky.cc/translations/anthropic/tool-use-2-workflow/https://ai.flicky.cc/translations/anthropic/tool-use/https://ai.flicky.cc/translations/china-courses/d2l-zh-0-guide/https://ai.flicky.cc/translations/china-courses/d2l-zh-1-terminology/https://ai.flicky.cc/translations/china-courses/d2l-zh-2-multi-gpu/https://ai.flicky.cc/translations/china-courses/happy-llm-0-overview/https://ai.flicky.cc/translations/china-courses/happy-llm-1-nlp-basics/https://ai.flicky.cc/translations/china-courses/happy-llm-2-transformer/https://ai.flicky.cc/translations/china-courses/happy-llm-3-pretrained-lm/https://ai.flicky.cc/translations/china-courses/happy-llm-4-llm/https://ai.flicky.cc/translations/china-courses/happy-llm-5-build-llm/https://ai.flicky.cc/translations/china-courses/happy-llm-6-preference-rl/https://ai.flicky.cc/translations/china-courses/happy-llm-6-training/https://ai.flicky.cc/translations/china-courses/happy-llm-7-applications/https://ai.flicky.cc/translations/china-courses/happy-llm-8-1-grpo/https://ai.flicky.cc/translations/china-courses/happy-llm-8-2-opd/https://ai.flicky.cc/translations/china-courses/happy-llm-8-3-search-r1/https://ai.flicky.cc/translations/china-courses/happy-llm-8-4-retool/https://ai.flicky.cc/translations/china-courses/hylee-0-overview-homework/https://ai.flicky.cc/translations/china-courses/hylee-genai-2024-1/https://ai.flicky.cc/translations/china-courses/hylee-genai-2024-2/https://ai.flicky.cc/translations/china-courses/hylee-genai-2024-3/https://ai.flicky.cc/translations/china-courses/hylee-ml-2025-1/https://ai.flicky.cc/translations/china-courses/hylee-ml-2025-2/https://ai.flicky.cc/translations/china-courses/hylee-ml-2026-1/https://ai.flicky.cc/translations/china-courses/hylee-ml-2026-2/https://ai.flicky.cc/translations/china-courses/hylee-ml-2026-3/https://ai.flicky.cc/translations/china-courses/llmbook-0-guide/https://ai.flicky.cc/translations/china-courses/llmbook-1-pretraining/https://ai.flicky.cc/translations/china-courses/llmbook-2-alignment-deploy/https://ai.flicky.cc/translations/china-courses/llmbook-3-prompting-agents-eval/https://ai.flicky.cc/translations/china-courses/self-llm-0-guide/https://ai.flicky.cc/translations/china-courses/self-llm-1-qwen3-vllm/https://ai.flicky.cc/translations/china-courses/self-llm-2-qwen3-lora/https://ai.flicky.cc/translations/china-courses/tiny-universe-0-guide/https://ai.flicky.cc/translations/china-courses/tiny-universe-1-tinyllm/https://ai.flicky.cc/translations/china-courses/tiny-universe-2-qwen-blog/https://ai.flicky.cc/translations/china-courses/tiny-universe-3-tinyrag/https://ai.flicky.cc/translations/china-courses/tiny-universe-4-tinyagent/https://ai.flicky.cc/translations/china-courses/tiny-universe-5-tinyeval/https://ai.flicky.cc/translations/china-courses/tiny-universe-6-tinydiffusion/https://ai.flicky.cc/translations/china-labs/alibaba-acp-1-guide/https://ai.flicky.cc/translations/china-labs/alibaba-acp-2-rag/https://ai.flicky.cc/translations/china-labs/ascend-llm-dev-guide/https://ai.flicky.cc/translations/china-labs/ernie-reports/https://ai.flicky.cc/translations/china-labs/glm-cookbook-guide/https://ai.flicky.cc/translations/china-labs/internlm-camp-1-guide/https://ai.flicky.cc/translations/china-labs/internlm-camp-2-key-tutorials/https://ai.flicky.cc/translations/china-labs/kimi-k2-tool-calling/https://ai.flicky.cc/translations/china-labs/minimax-m2-full-attention/https://ai.flicky.cc/translations/china-labs/modelscope-classroom-1-guide/https://ai.flicky.cc/translations/china-labs/modelscope-classroom-2-ppo-grpo/https://ai.flicky.cc/translations/china-labs/modelscope-classroom-3-continuous-batching/https://ai.flicky.cc/translations/china-labs/qwen-agent-1-guide/https://ai.flicky.cc/translations/china-labs/qwen-agent-2-readme/https://ai.flicky.cc/translations/china-labs/qwen-blog-1-qwen3/https://ai.flicky.cc/translations/china-labs/qwen-blog-2-gspo/https://ai.flicky.cc/translations/china-labs/qwen-blog-3-global-load-balance/https://ai.flicky.cc/translations/china-labs/qwen-docs-1-guide/https://ai.flicky.cc/translations/china-labs/qwen-docs-2-deploy/https://ai.flicky.cc/translations/china-labs/qwen-docs-3-function-calling/https://ai.flicky.cc/translations/china-labs/qwen-docs-4-finetuning/https://ai.flicky.cc/translations/china-labs/verl-1-quickstart/https://ai.flicky.cc/translations/china-labs/verl-2-grpo/https://ai.flicky.cc/translations/china-labs/verl-3-four-gpus/https://ai.flicky.cc/translations/deepseek/3fs-design-notes/https://ai.flicky.cc/translations/deepseek/api-docs-guide/https://ai.flicky.cc/translations/deepseek/deepseek-overview/https://ai.flicky.cc/translations/deepseek/dualpipe-eplb/https://ai.flicky.cc/translations/deepseek/flashmla-ascend-deep-dive/https://ai.flicky.cc/translations/deepseek/flashmla-deep-dive/https://ai.flicky.cc/translations/deepseek/inference-system-v3-r1/https://ai.flicky.cc/translations/deepseek/report-deepseek-llm/https://ai.flicky.cc/translations/deepseek/report-deepseek-v2-mla/https://ai.flicky.cc/translations/deepseek/report-deepseek-v3-2/https://ai.flicky.cc/translations/deepseek/report-deepseek-v4/https://ai.flicky.cc/translations/deepseek/report-deepseekmath-grpo/https://ai.flicky.cc/translations/deepseek/report-deepseekmoe/https://ai.flicky.cc/translations/google/ai-foundations-1-ngrams/https://ai.flicky.cc/translations/google/ai-foundations-1-slm/https://ai.flicky.cc/translations/google/ai-foundations-2-bpe-embeddings/https://ai.flicky.cc/translations/google/ai-foundations-2-data/https://ai.flicky.cc/translations/google/ai-foundations-3-mlp/https://ai.flicky.cc/translations/google/ai-foundations-3-training/https://ai.flicky.cc/translations/google/ai-foundations-4-parameters/https://ai.flicky.cc/translations/google/ai-foundations-4-transformer/https://ai.flicky.cc/translations/google/ai-foundations-5-finetuning/https://ai.flicky.cc/translations/google/ai-foundations-5-lora/https://ai.flicky.cc/translations/google/ai-foundations-7-bf16/https://ai.flicky.cc/translations/google/ai-foundations-7-compute/https://ai.flicky.cc/translations/google/ai-foundations-8-capstone/https://ai.flicky.cc/translations/google/ai-foundations-overview/https://ai.flicky.cc/translations/google/scaling-book-0-overview/https://ai.flicky.cc/translations/google/scaling-book-1-roofline/https://ai.flicky.cc/translations/google/scaling-book-2-tpus/https://ai.flicky.cc/translations/google/scaling-book-3-sharding/https://ai.flicky.cc/translations/google/scaling-book-4-transformers/https://ai.flicky.cc/translations/google/scaling-book-5-training/https://ai.flicky.cc/translations/google/scaling-book-7-inference/https://ai.flicky.cc/translations/google/scaling-book-12-gpus/https://ai.flicky.cc/translations/google/tuning-playbook-1-start/https://ai.flicky.cc/translations/google/tuning-playbook-2-scientific/https://ai.flicky.cc/translations/google/tuning-playbook-3-training-faq/https://ai.flicky.cc/translations/huggingface/deep-rl-0-overview/https://ai.flicky.cc/translations/huggingface/deep-rl-1-intro/https://ai.flicky.cc/translations/huggingface/deep-rl-1-lunar-lander/https://ai.flicky.cc/translations/huggingface/deep-rl-2-frozenlake-taxi/https://ai.flicky.cc/translations/huggingface/deep-rl-2-q-learning/https://ai.flicky.cc/translations/huggingface/deep-rl-3-dqn/https://ai.flicky.cc/translations/huggingface/deep-rl-4-policy-gradient/https://ai.flicky.cc/translations/huggingface/deep-rl-4-reinforce/https://ai.flicky.cc/translations/huggingface/deep-rl-5-7-unity-bonus/https://ai.flicky.cc/translations/huggingface/deep-rl-6-actor-critic/https://ai.flicky.cc/translations/huggingface/deep-rl-8-ppo-practice/https://ai.flicky.cc/translations/huggingface/deep-rl-8-ppo/https://ai.flicky.cc/translations/huggingface/dlai-quantization-guide/https://ai.flicky.cc/translations/huggingface/eval-guidebook-1-automated-benchmarks/https://ai.flicky.cc/translations/huggingface/eval-guidebook-2-judges-humans/https://ai.flicky.cc/translations/huggingface/eval-guidebook-3-troubleshooting/https://ai.flicky.cc/translations/huggingface/hf-agents-course/https://ai.flicky.cc/translations/huggingface/hf-cookbook-guide/https://ai.flicky.cc/translations/huggingface/hf-diffusion-1-from-scratch/https://ai.flicky.cc/translations/huggingface/hf-diffusion-1-intro/https://ai.flicky.cc/translations/huggingface/hf-diffusion-2-guidance/https://ai.flicky.cc/translations/huggingface/hf-diffusion-3-stable-diffusion/https://ai.flicky.cc/translations/huggingface/hf-diffusion-4-further/https://ai.flicky.cc/translations/huggingface/hf-llm-course-10-argilla/https://ai.flicky.cc/translations/huggingface/hf-llm-course-11-finetuning/https://ai.flicky.cc/translations/huggingface/hf-llm-course-12-grpo-math/https://ai.flicky.cc/translations/huggingface/hf-llm-course-12-grpo-practice/https://ai.flicky.cc/translations/huggingface/hf-llm-course-12-rl-r1/https://ai.flicky.cc/translations/huggingface/hf-llm-course-overview/https://ai.flicky.cc/translations/huggingface/hf-mcp-course-1-concepts/https://ai.flicky.cc/translations/huggingface/hf-mcp-course-1-sdk-clients/https://ai.flicky.cc/translations/huggingface/hf-mcp-course-2-app/https://ai.flicky.cc/translations/huggingface/hf-mcp-course/https://ai.flicky.cc/translations/huggingface/hf-smol-course-2-dpo/https://ai.flicky.cc/translations/huggingface/hf-smol-course-3-vlm/https://ai.flicky.cc/translations/huggingface/hf-smol-course/https://ai.flicky.cc/translations/huggingface/smol-training-playbook-1-pretraining/https://ai.flicky.cc/translations/huggingface/smol-training-playbook-2-posttraining-infra/https://ai.flicky.cc/translations/huggingface/ultrascale-1-one-gpu/https://ai.flicky.cc/translations/huggingface/ultrascale-2-dp-zero-tp/https://ai.flicky.cc/translations/huggingface/ultrascale-3-cp-pp-ep-5d/https://ai.flicky.cc/translations/huggingface/ultrascale-4-gpu-kernels/https://ai.flicky.cc/translations/karpathy/deep-dive-llms/https://ai.flicky.cc/translations/karpathy/how-i-use-llms/https://ai.flicky.cc/translations/karpathy/microgpt/https://ai.flicky.cc/translations/karpathy/nanochat/https://ai.flicky.cc/translations/karpathy/zero-to-hero-1-micrograd/https://ai.flicky.cc/translations/karpathy/zero-to-hero-2-makemore-bigrams/https://ai.flicky.cc/translations/karpathy/zero-to-hero-3-makemore-mlp/https://ai.flicky.cc/translations/karpathy/zero-to-hero-4-batchnorm/https://ai.flicky.cc/translations/karpathy/zero-to-hero-5-backprop-ninja/https://ai.flicky.cc/translations/karpathy/zero-to-hero-6-wavenet/https://ai.flicky.cc/translations/karpathy/zero-to-hero-7-gpt/https://ai.flicky.cc/translations/karpathy/zero-to-hero-8-tokenizer/https://ai.flicky.cc/translations/karpathy/zero-to-hero-9-gpt2/https://ai.flicky.cc/translations/meta-nvidia/llama-cookbook/https://ai.flicky.cc/translations/meta-nvidia/mistral-cookbook/https://ai.flicky.cc/translations/meta-nvidia/mlu-explain-1-train-test-validation/https://ai.flicky.cc/translations/meta-nvidia/mlu-explain-2-bias-variance/https://ai.flicky.cc/translations/meta-nvidia/nvidia-ach-1-guide/https://ai.flicky.cc/translations/meta-nvidia/nvidia-ach-2-gpu-cuda-basics/https://ai.flicky.cc/translations/meta-nvidia/nvidia-ach-3-cupy-numba/https://ai.flicky.cc/translations/meta-nvidia/nvidia-dli/https://ai.flicky.cc/translations/meta-nvidia/pytorch-basics-1-quickstart-tensors/https://ai.flicky.cc/translations/meta-nvidia/pytorch-basics-2-data/https://ai.flicky.cc/translations/meta-nvidia/pytorch-basics-3-model-autograd/https://ai.flicky.cc/translations/meta-nvidia/pytorch-basics-4-train-save/https://ai.flicky.cc/translations/openai/dlai-prompt-engineering-and-o1/https://ai.flicky.cc/translations/openai/dlai-rlhf-google-cloud/https://ai.flicky.cc/translations/openai/openai-cookbook-eval-flywheel/https://ai.flicky.cc/translations/openai/openai-cookbook-function-calling/https://ai.flicky.cc/translations/openai/openai-cookbook-guide/https://ai.flicky.cc/translations/openai/openai-cookbook-rag-embeddings/https://ai.flicky.cc/translations/openai/practical-guide-to-building-agents/https://ai.flicky.cc/translations/openai/spinning-up-exercises/https://ai.flicky.cc/translations/openai/spinning-up-intro/https://ai.flicky.cc/translations/openai/spinning-up-key-papers/https://ai.flicky.cc/translations/openai/spinning-up-part-1-key-concepts/https://ai.flicky.cc/translations/openai/spinning-up-part-2-kinds-of-algorithms/https://ai.flicky.cc/translations/openai/spinning-up-part-3-policy-optimization/https://ai.flicky.cc/translations/openai/spinning-up-researcher/https://ai.flicky.cc/translations/openai/spinning-up-trpo-ddpg-td3-sac/https://ai.flicky.cc/translations/openai/spinning-up-vpg-ppo/https://ai.flicky.cc/translations/people/ahead-of-ai-guide/https://ai.flicky.cc/translations/people/arena-guide/https://ai.flicky.cc/translations/people/colah-backprop/https://ai.flicky.cc/translations/people/colah-lstm/https://ai.flicky.cc/translations/people/colah-manifolds-topology/https://ai.flicky.cc/translations/people/colah-nlp-representations/https://ai.flicky.cc/translations/people/distill-augmented-rnns/https://ai.flicky.cc/translations/people/distill-feature-visualization/https://ai.flicky.cc/translations/people/distill-momentum/https://ai.flicky.cc/translations/people/distill-zoom-in/https://ai.flicky.cc/translations/people/lillog-llm-agents/https://ai.flicky.cc/translations/people/lillog-policy-gradient/https://ai.flicky.cc/translations/people/lillog-prompt-engineering/https://ai.flicky.cc/translations/people/lillog-reward-hacking/https://ai.flicky.cc/translations/people/lillog-transformer-family/https://ai.flicky.cc/translations/people/lillog-why-we-think/https://ai.flicky.cc/translations/people/udl-guide/https://ai.flicky.cc/translations/people/umar-jamil-guide/https://ai.flicky.cc/translations/stanford/cs25-guide/https://ai.flicky.cc/translations/stanford/cs224n-1-word-vectors/https://ai.flicky.cc/translations/stanford/cs224n-2-rnn-seq2seq-attention/https://ai.flicky.cc/translations/stanford/cs224n-guide/https://ai.flicky.cc/translations/stanford/cs229-1-supervised/https://ai.flicky.cc/translations/stanford/cs229-2-svm-learning-theory/https://ai.flicky.cc/translations/stanford/cs229-3-deep-learning-unsupervised/https://ai.flicky.cc/translations/stanford/cs229-guide/https://ai.flicky.cc/translations/stanford/cs231n-1-linear-classify/https://ai.flicky.cc/translations/stanford/cs231n-2-optimization/https://ai.flicky.cc/translations/stanford/cs231n-3-backprop/https://ai.flicky.cc/translations/stanford/cs231n-4-cnn-layers/https://ai.flicky.cc/translations/stanford/cs231n-5-cnn-architectures/https://ai.flicky.cc/translations/stanford/cs231n-guide/https://ai.flicky.cc/translations/stanford/cs336-a1-basics/https://ai.flicky.cc/translations/stanford/cs336-a2-systems/https://ai.flicky.cc/translations/stanford/cs336-a3-scaling/https://ai.flicky.cc/translations/stanford/cs336-a4-data/https://ai.flicky.cc/translations/stanford/cs336-a5-alignment/https://ai.flicky.cc/translations/stanford/cs336-l01-02-tokenization-resources/https://ai.flicky.cc/translations/stanford/cs336-l03-04-architectures-moe/https://ai.flicky.cc/translations/stanford/cs336-l05-06-gpus-kernels/https://ai.flicky.cc/translations/stanford/cs336-l07-08-parallelism/https://ai.flicky.cc/translations/stanford/cs336-l09-11-scaling-laws/https://ai.flicky.cc/translations/stanford/cs336-l10-12-inference-evaluation/https://ai.flicky.cc/translations/stanford/cs336-l13-14-data/https://ai.flicky.cc/translations/stanford/cs336-l15-16-sft-rlhf-rlvr/https://ai.flicky.cc/translations/stanford/cs336-l17-policy-gradient-wrapup/https://ai.flicky.cc/translations/stanford/cs336-overview/https://ai.flicky.cc/translations/universities/berkeley-llm-agents-guide/https://ai.flicky.cc/translations/universities/cmu-llm-systems-guide/https://ai.flicky.cc/translations/universities/llm-visualization/https://ai.flicky.cc/translations/universities/matrix-calculus-1-linear-operators/https://ai.flicky.cc/translations/universities/matrix-calculus-2-matrix-gradients/https://ai.flicky.cc/translations/universities/matrix-calculus-3-autodiff/https://ai.flicky.cc/translations/universities/matrix-calculus-guide/https://ai.flicky.cc/translations/universities/mit-6s191-1-foundations/https://ai.flicky.cc/translations/universities/mit-6s191-2-generative-rl/https://ai.flicky.cc/translations/universities/mit-6s191-3-guest-lectures/https://ai.flicky.cc/translations/universities/mit-6s191-guide/https://ai.flicky.cc/translations/universities/mit-6s191-lab1-music/https://ai.flicky.cc/translations/universities/mit-6s191-lab2-vision/https://ai.flicky.cc/translations/universities/mit-6s191-lab3-llm/https://ai.flicky.cc/translations/universities/mit-1806-1-transformations/https://ai.flicky.cc/translations/universities/mit-1806-2-rank/https://ai.flicky.cc/translations/universities/mit-1806-3-eigenvalues/https://ai.flicky.cc/translations/universities/mit-1806-4-svd/https://ai.flicky.cc/translations/universities/mit-1806-guide/https://ai.flicky.cc/translations/universities/transformer-explainer/