語言模型練功坊
| s? | No. | Model | Task | Author |
|---|---|---|---|---|
| s6 | ||||
| 04 | BERT | CoLA Sentence Classification | @tomy0000000 | |
| 07 | MiniLM | mrpc Sentence Classification | @l53513955 | |
| s7 | ||||
| 03 | BERT | QNLI Sentence Classification | @huang624 | |
| 05 | BART | SQuAD Question Answering | @HankyStyle | |
| s8 | ||||
| 06 | BERT | mrpc Sentence Classification | @leonardo-lin | |
| 08 | BERT | SQuAD 2.0 Question Answering | @gigilin7 | |
| 09 | BERT | DRCD Question Answering | @salmon-Xin | |
| 10 | mBART | DRCD Question Generation | @good22014040 | |
| 11 | BART | cnn_dailymail summarization | @dan890407 | |
| 12 | BART | SQuAD Question Generation | @s1072954 | |
| s9 | ||||
| 13 | BERT | glue_qnli QA entailment | @SinSuan | |
| 14 | BERT | chinese_abstractive_corpus text summarization | @nderrrrr | |
| 15 | mT5 | iwslt2017 translation | @seanx12345 | |
| 16 | RoBERTa | glue_stsb Sentence similarity | @puppyyyo | |
| 17 | BART | llama2 chat 7b QLoRA gbharti/finance-alpaca | @allen3325 | |
| 18 | BART | Fine Tuning Zephyr7B GSM8K (math) | @cc3374twa | |
| s10 | ||||
| 19 | BERT | Train Model Workflow and Huggingface | @Coby0228 | |
| 20 | BERT | Trainer and Tensorboard | @adsl135789 | |
| 21 | BERT | Pipeline and Decoding Strategy | @IdONTKnowCHEK | |
| 22 | Llama-3.2-3B-Instruct | Demo LoRA and QLoRA | @Rui0828 | |
| 23 | Llama-3.2-1B | Distributed Inference | @yumeow0122 |