librarian-bot's picture
Librarian Bot: Add base_model information to model
af1f181
|
raw
history blame
472 Bytes
---
library_name: peft
base_model: mosama/llama2-rope-scaled
---
## 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: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0