NLP Wiki

User Tools

Site Tools

Trace: • structured_prediction • systems_ml • causality • rule-based_systems • nn_tricks • named_entity_recognition • ai_singularity • gamification • corpus_analysis • mechanistic_interpretability
nlp:pretraining

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
nlp:pretraining [2026/08/03 03:13] – [Pretraining (and Post-training) Methodology] jmflanignlp:pretraining [2026/08/03 03:13] (current) – [Pretraining (and Post-training) Methodology] jmflanig
Line 125: Line 125:
     * [[https://arxiv.org/pdf/2512.02556|2025 - DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models]]     * [[https://arxiv.org/pdf/2512.02556|2025 - DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models]]
     * [[https://arxiv.org/pdf/2606.19348|2026 - DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence]]     * [[https://arxiv.org/pdf/2606.19348|2026 - DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence]]
-    * [[https://arxiv.org/pdf/2607.02770|Google 2026 - Gemma 4 Technical Report]]+    * [[https://arxiv.org/pdf/2607.02770|Google Team 2026 - Gemma 4 Technical Report]]
   * **Closed Model System Cards**   * **Closed Model System Cards**
     * These sometimes contain some interesting information, especially OpenAI's system cards     * These sometimes contain some interesting information, especially OpenAI's system cards
nlp/pretraining.txt · Last modified: 2026/08/03 03:13 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki