大模型自用资料。
- DeepSeek-VL2: https://github.com/deepseek-ai/DeepSeek-VL2/blob/main/DeepSeek_VL2_paper.pdf https://arxiv.org/pdf/2412.10302
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs viaReinforcement Learning https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf
- DeepSeek-V3 Technical Report https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf
- DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence https://arxiv.org/pdf/2401.14196
- let's verify step by step: https://arxiv.org/pdf/2305.20050
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters: https://arxiv.org/pdf/2408.03314
- ChatGLM2 CODE
- LLaMA: Open and Efficient Foundation Language Models PDF CODE
- ChatGLM CODE
- PaLM: Scaling Language Modeling with Pathways PDF
- InstructGPT PDF
- GPT 3.0 PDF
- T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer PDF CODE
- GPT 2.0 PDF
- GPT 1.0 PDF
- BERT PDF
- Transformers PDF
- transformer-explainer https://poloclub.github.io/transformer-explainer
- The Illustrated Transformer http://jalammar.github.io/illustrated-transformer/