Útmutatóhoz kapcsolódó kvíz · Kemény Szint
DeepSeek V3 és R1 érvelési kvíz
Test DeepSeek-V3 and R1's MoE architecture, reported training compute, RL pipeline, and distilled releases from the original reports.
kérdés 1 -ból 8
What parameter counts did the DeepSeek-V3 technical report give?
Tekintse meg az összes kérdést8 kérdéseket
A válaszok és magyarázatok megjelennek a kvíz kitöltésekor.
- What parameter counts did the DeepSeek-V3 technical report give?
- 671B total parameters, with 37B activated per token
- 37B total parameters, all active per token
- 671B active parameters for every token
- A dense model with no routed experts
- What was notable about DeepSeek-R1’s reasoning training and release?
- It used no training data
- The report describes RL-based reasoning and publicly released model weights
- It was only a closed cloud API
- It was a rule-based program with no learned model
- What compute figure did the DeepSeek-V3 report give for its full training run?
- 2.788 thousand CPU-hours
- 2.788 million H100 GPU-hours for R1 only
- 2.788 million H800 GPU-hours
- No accelerator-hours were reported
- What training signal helped DeepSeek-R1 develop reasoning behaviors?
- Only manually written rules with no learned model
- Image-label classification
- Random rewards unrelated to answers
- Reinforcement learning rewards for correct, verifiable outcomes
- Milyen hatékonysági technika társul a DeepSeek-V3 edzéséhez?
- Többfejes látens figyelem és kiegészítő veszteségmentes terheléselosztás
- A modell nyomtatása papírra
- Az összes figyelemréteg eltávolítása
- Képzés egyetlen példán
- Which types of tasks did the DeepSeek-R1 paper evaluate?
- Csak képbesorolás
- Mathematics, coding competitions, and STEM tasks
- Only speech transcription
- Only spreadsheet formatting
- What supervised-learning step does the DeepSeek-R1 pipeline use before its first RL stage?
- A period of training with no text or prompts
- A final model-compression step only
- Cold-start supervised fine-tuning on curated reasoning examples
- A computer-vision pretraining stage
- Which model families were used as bases for the released R1-distilled models?
- BERT and CLIP
- Tacotron and WavLM
- NeRF and Instant-NGP
- Qwen and Llama