Allenpai commited on
Commit
33e64a5
1 Parent(s): edafdab

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Training procedure
2
+
3
+ The following bitsandbytes quantization config was used during training:
4
+
5
+ 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
6
+
7
+ Framework versions
8
+
9
+ PEFT 0.4.0.dev0