Start of the encoder’s training
×Checkpoint
“We train a vision encoder named DeepSeek-ViT from scratch”: a model of its own, trained before it joins the language model.
- Weights
- no pinned source shows them published
Sources1
- DeepSeek_V41_Tech_Report.pdf, p. 8Checkpoint
Key
- stage
- tokens, log scale
- a total no source states, computed from steps × batch × length
- checkpoint
- checkpoint, weights published
- a join the sources leave unexplained
- stages of a released model, folded into one row
- derived
- computed from reported values; the arithmetic is shown
- not disclosed
- no pinned source states it; nothing is filled in