Short Course Q&A Post-training of LLMs
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
|
DPO performed on the provided code-lab leads to gibberish result
|
|
4 | 84 | July 2, 2026 |
|
L3 : While loading Qwen model it throws TypeError: argument of type 'NoneType' is not iterable
|
|
2 | 167 | May 2, 2026 |
|
Error in the LoRa matrices of the third video
|
|
0 | 15 | September 9, 2025 |
|
Dataset used for fine-tuning banghua/Qwen3-0.6B-SFT
|
|
5 | 476 | July 28, 2025 |
|
Resources download for code replication
|
|
0 | 64 | July 11, 2025 |
|
SFTTrainer is using wandb.ai
|
|
4 | 148 | July 12, 2025 |
|
Parameter Finetuning
|
|
0 | 47 | July 9, 2025 |
|
MCP vs Post-Training of LLMs
|
|
0 | 158 | July 9, 2025 |