Short Course Q&A Pretraining LLMs
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
|
Packing the data with max sequence length
|
|
3 | 11 | December 19, 2024 |
|
Data packing
|
|
0 | 15 | September 26, 2024 |
|
Why does the model start repeating the same sentences after some N number of token outputs?
|
|
3 | 67 | September 25, 2024 |
|
Number of tokens mentioned in the first video to train a 248M model
|
|
0 | 14 | September 12, 2024 |
|
L2_language_model.bin not found
|
|
3 | 40 | August 29, 2024 |
|
Korean subtitles for Pretraining LLMs courses
|
|
0 | 20 | July 31, 2024 |
|
About packaging data: NEXT SENTECE
|
|
0 | 38 | July 19, 2024 |