dieusangly commited on
Commit
a7dcfb0
·
1 Parent(s): 6e8908d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -25
README.md CHANGED
@@ -3,18 +3,6 @@ library_name: peft
3
  ---
4
  ## Training procedure
5
 
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - load_in_8bit: False
9
- - load_in_4bit: True
10
- - llm_int8_threshold: 6.0
11
- - llm_int8_skip_modules: None
12
- - llm_int8_enable_fp32_cpu_offload: False
13
- - llm_int8_has_fp16_weight: False
14
- - bnb_4bit_quant_type: nf4
15
- - bnb_4bit_use_double_quant: True
16
- - bnb_4bit_compute_dtype: float16
17
-
18
  The following `bitsandbytes` quantization config was used during training:
19
  - load_in_8bit: False
20
  - load_in_4bit: True
@@ -26,19 +14,6 @@ The following `bitsandbytes` quantization config was used during training:
26
  - bnb_4bit_use_double_quant: True
27
  - bnb_4bit_compute_dtype: float16
28
 
29
- The following `bitsandbytes` quantization config was used during training:
30
- - load_in_8bit: False
31
- - load_in_4bit: True
32
- - llm_int8_threshold: 6.0
33
- - llm_int8_skip_modules: None
34
- - llm_int8_enable_fp32_cpu_offload: False
35
- - llm_int8_has_fp16_weight: False
36
- - bnb_4bit_quant_type: nf4
37
- - bnb_4bit_use_double_quant: True
38
- - bnb_4bit_compute_dtype: bfloat16
39
  ### Framework versions
40
 
41
  - PEFT 0.4.0
42
- - PEFT 0.4.0
43
-
44
- - PEFT 0.4.0
 
3
  ---
4
  ## Training procedure
5
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  The following `bitsandbytes` quantization config was used during training:
7
  - load_in_8bit: False
8
  - load_in_4bit: True
 
14
  - bnb_4bit_use_double_quant: True
15
  - bnb_4bit_compute_dtype: float16
16
 
 
 
 
 
 
 
 
 
 
 
17
  ### Framework versions
18
 
19
  - PEFT 0.4.0