---
license: other
library_name: peft
base_model: TheBloke/Llama-2-13B-fp16
---
## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions


- PEFT 0.5.0

I'm NOT the author of this work.

I cite anon :

```shell
feel free to reupload to hf for posterity
```

Credit to "anon49"