metadata
library_name: peft
自回归语言模型BLOOMZ对应角色性格LORA
(角色:原神莫娜,任务:根据三个实体信息以及一个日程提示文本生成该角色的日程提示文本,可在端侧4GB内部署)
Training procedure
The following bitsandbytes
quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
Framework versions
- PEFT 0.4.0
在线使用连接,测试T5-普通内存下可用,运行约5min
https://colab.research.google.com/drive/12zKnvIAEqGCt2Qi_IS99GfTBbrzdMX8L?usp=sharing