mirror of
https://github.com/wassname/peft.git
synced 2026-09-25 13:50:20 +08:00
d5c0c7e32c7da135ab30271b78b6462aa7b21e8e
🤗 pets
Parameter-Efficient Tuning at Scale with 🤗 Accelerate
Supported moethods:
- Prefix Tuning
- P-Tuning
- Prompt Tuning
- LoRA [in progress]
Models support matrix
Sequence Classification
| Prefix Tuning | P-Tuning | Prompt Tuning | LoRA | |
|---|---|---|---|---|
| BERT | ✅ | ✅ | ✅ | |
| RoBERTa | ✅ | ✅ | ✅ | |
| GPT-2 | ✅ | ✅ | ✅ | |
| Bloom | ✅ | ✅ | ✅ | |
| OPT | ✅ | ✅ | ✅ | |
| GPT-Neo | ✅ | ✅ | ✅ | |
| GPT-J | ✅ | ✅ | ✅ | |
| Deberta | ||||
| Deberta-v2 |
Causal Language Modeling
| Prefix Tuning | P-Tuning | Prompt Tuning | LoRA | |
|---|---|---|---|---|
| GPT-2 | ||||
| Bloom | ||||
| OPT | ||||
| GPT-Neo | ||||
| GPT-J | ||||
| BART |
Conditional Generation
| Prefix Tuning | P-Tuning | Prompt Tuning | LoRA | |
|---|---|---|---|---|
| T5 | ||||
| BART |
Languages
Python
99.8%
Makefile
0.2%