skywalker290 commited on
Commit
536def0
1 Parent(s): cd80f4c

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +47 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-560m",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4
28
+ },
29
+ "layer_norm_epsilon": 1e-05,
30
+ "masked_softmax_fusion": true,
31
+ "model_type": "bloom",
32
+ "n_head": 16,
33
+ "n_inner": null,
34
+ "n_layer": 24,
35
+ "offset_alibi": 100,
36
+ "pad_token_id": 3,
37
+ "pretraining_tp": 1,
38
+ "problem_type": "multi_label_classification",
39
+ "skip_bias_add": true,
40
+ "skip_bias_add_qkv": false,
41
+ "slow_but_exact": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.40.0",
44
+ "unk_token_id": 0,
45
+ "use_cache": true,
46
+ "vocab_size": 250880
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d428ced5cebf8f72e7f38f2fceb1d5236407005084b061b0dc70ea8ed5cbd25
3
+ size 2236912864
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bec41e2bddf1a831cd991347c74ad24b229215698f1c400673650f24d73663
3
+ size 4984