Alternative names (6)
fineTunable • fineTunedBy • fineTunedFor • fineTunedFrom • fineTunedOn • fineTuningMethodRandom triples
| Subject | Object |
|---|---|
| gptkb:LLaMA_2-Chat | safety |
| gptkb:OpenAssistant/pythia-12b-sft-v8-128k-steps | supervised fine-tuning |
| gptkb:OpenAssistant/pythia-12b-sft-v8-32k-steps | OpenAssistant dataset |
| gptkb:RoBERTa | question answering |
| gptkb:Text-To-Text_Transfer_Transformer | yes |
| gptkb:OpenAssistant/oasst-sft-1-pythia-12b | OASST1 dataset |
| gptkb:Nous_Hermes_2_Yi | gptkb:Hermes_2_dataset |
| gptkb:Mixtral_8x7B | true |
| gptkb:Falcon-40B | true |
| gptkb:Yi-7B | true |
| gptkb:OpenAssistant/pythia-12b-sft-v8-2s-steps | supervised fine-tuning (SFT) |
| gptkb:DeBERTa-v2 | true |
| gptkb:BERT-large | true |
| gptkb:FLAN-T5 | instruction datasets |
| gptkb:OpenAssistant/pythia-12b-sft-v8-8b-steps | supervised fine-tuning (SFT) |
| gptkb:Llama_2 | chat |
| gptkb:Llama_2_7B_Instruct | question answering |
| gptkb:Meta_Llama_2 | true |
| gptkb:OpenAssistant/pythia-12b-sft-v8-1s-steps | supervised fine-tuning (SFT) |
| gptkb:DeBERTa-Base | true |