Allenpai commited on
Commit
398206f
1 Parent(s): 5f29007

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  The following bitsandbytes quantization config was used during training:
2
 
3
- 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
4
 
5
  Framework versions
6
 
 
1
  The following bitsandbytes quantization config was used during training:
2
 
3
+ load_in_8bit: True
4
 
5
  Framework versions
6