---
library_name: peft
datasets:
- pankajmathur/lima_unchained_v1
base_model: tiiuae/falcon-180B
---

Made in collaboration with [Pankaj Mathur](https://huggingface.co/pankajmathur)

## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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 0.6.0.dev0