Hugging Face's logo

jmgb0127
/
bloom-lotr

PEFT
Model card Files Community
1
jmgb0127 commited on
Commit
a13f53f
•
1 Parent(s): e07e003

Upload model

Browse files
Files changed (2) hide show
  1. README.md +5 -5
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -5,15 +5,15 @@ library_name: peft
5
 
6
 
7
  The following `bitsandbytes` quantization config was used during training:
8
- - load_in_8bit: True
9
- - load_in_4bit: False
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: fp4
15
- - bnb_4bit_use_double_quant: False
16
- - bnb_4bit_compute_dtype: float32
17
  ### Framework versions
18
 
19
 
 
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: bfloat16
17
  ### Framework versions
18
 
19
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f919e852462bbe8b81b90e9bcb06fcd3794026f3d59401455812a457e3634fbd
3
  size 19683045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4128b075a8bd7d78f4c058cd7e2931904abc45db927cfaa1ff48240872793f10
3
  size 19683045