Hugging Face's logo

CreatorPhan
/
Wiki_full

PEFT
Model card Files Community
8
CreatorPhan commited on
Commit
dc202b3
•
1 Parent(s): 744e56f

Upload folder using huggingface_hub (#4)

Browse files

- Upload folder using huggingface_hub (489319e7f7d777e0d6c8bccb32af567c47605427)

Files changed (7) hide show
  1. README.md +13 -0
  2. adapter_model.bin +1 -1
  3. optimizer.pt +1 -1
  4. rng_state.pth +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,18 @@ library_name: peft
4
  ## Training procedure
5
 
6
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - quant_method: bitsandbytes
9
  - load_in_8bit: True
@@ -17,5 +29,6 @@ The following `bitsandbytes` quantization config was used during training:
17
  - bnb_4bit_compute_dtype: float32
18
  ### Framework versions
19
 
 
20
 
21
  - PEFT 0.6.0.dev0
 
4
  ## Training procedure
5
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
  The following `bitsandbytes` quantization config was used during training:
20
  - quant_method: bitsandbytes
21
  - load_in_8bit: True
 
29
  - bnb_4bit_compute_dtype: float32
30
  ### Framework versions
31
 
32
+ - PEFT 0.6.0.dev0
33
 
34
  - PEFT 0.6.0.dev0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc8aa748553051f477f8856a04dab6c16386e77b50764d21abc20a51512c7c1e
3
  size 39409357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297ef8417e7df986ce834d9b0c8ebd28197873ea409686414f04e91b74281978
3
  size 39409357
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:980ce4082f86e8643d829ecc076ea00335d9e2d80d18c421ae802d241b9e3197
3
  size 78844421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae8afe492977b67949412a751b16cf3c9e70d22ef10182d710a235c40cb1a4ac
3
  size 78844421
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5432f961e7c82cbe7b6ec30d027cf3db4d17372f65774be8cf037a208cbc1ac
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6162bb9db25c89c41e126a7a00a5d0695219447bff9b18d08731531620758440
3
  size 14575
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:203097d159784262bd5c95fedbda5673a26bd26ba8483bc4d9972c3ce0a53781
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5434e83c78ab052927972350ed56fbd84392b488b1d09a11bdb87201790659f
3
  size 627
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b610cbc4242bb50b4985b00e205994ae514fec6d9e2273f2b545a583a07b154b
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6a4742808b4bf3d45f92b24bdf7431a361a91d28d7901c45cf6a7781b8ab12
3
  size 4155