About
Adapter train using Qlora made for LLaMa2 7b Chat. This adapter adds the ability to fully, fluently and uninterruptedly speak other languages to LLaMa2.
Training procedure
The following bitsandbytes quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- 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: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.5.0.dev0
- Downloads last month
- 0
Unable to determine this model’s pipeline type. Check the
docs
.