Hugging Face's logo

Xenova
/
bloomz-560m

Text Generation
Transformers.js
ONNX
bloom
Model card Files
xet
Community
3
Xenova HF Staff commited on
Commit
ef9b204
·
1 Parent(s): c13d32c

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +4 -0
  2. config.json +32 -0
  3. generation_config.json +7 -0
  4. onnx/decoder_model.onnx +3 -0
  5. onnx/decoder_model.onnx_data +3 -0
  6. onnx/decoder_model_merged.onnx +3 -0
  7. onnx/decoder_model_merged.onnx_data +3 -0
  8. onnx/decoder_model_merged_quantized.onnx +3 -0
  9. onnx/decoder_model_quantized.onnx +3 -0
  10. onnx/decoder_with_past_model.onnx +3 -0
  11. onnx/decoder_with_past_model.onnx_data +3 -0
  12. onnx/decoder_with_past_model_quantized.onnx +3 -0
  13. quantize_config.json +104 -0
  14. special_tokens_map.json +6 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +11 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloomz-560m",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForCausalLM"
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
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_head": 16,
19
+ "n_inner": null,
20
+ "n_layer": 24,
21
+ "offset_alibi": 100,
22
+ "pad_token_id": 3,
23
+ "pretraining_tp": 1,
24
+ "seq_length": 2048,
25
+ "skip_bias_add": true,
26
+ "skip_bias_add_qkv": false,
27
+ "slow_but_exact": false,
28
+ "transformers_version": "4.33.0.dev0",
29
+ "unk_token_id": 0,
30
+ "use_cache": true,
31
+ "vocab_size": 250880
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.33.0.dev0"
7
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fb71c5ded414ab8f1cbd7d5746d6f52d8e9083205bb346528ca536ff80c849
3
+ size 708465
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f635b89653beb3954b0264474eddfbedf263eb0182b6aee0d8d753cf8e2d4dc
3
+ size 2236858368
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014c9564cd5e7b1d825a47c4cd12dba3b082031a16409d4daf05140b3e328b4f
3
+ size 1399544
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f635b89653beb3954b0264474eddfbedf263eb0182b6aee0d8d753cf8e2d4dc
3
+ size 2236858368
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca26a9704720663a3bd8713596d6e95023d5e320032ce717cfbf990da827345
3
+ size 562242269
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3a593ea5f6fe47aac5447109658d113489cef68c1448721b541c940965ff54
3
+ size 561214691
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e90698757af8933ef57252d2a16b3bb48752b8d7d0fa6cfa01c14b92b52d75
3
+ size 714978
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f635b89653beb3954b0264474eddfbedf263eb0182b6aee0d8d753cf8e2d4dc
3
+ size 2236858368
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d1b23f04c47b265bc4e8d335805f2b1844853a84c51c637d3f72a5a20a2f14
3
+ size 561216819
quantize_config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Sub",
8
+ "MatMul",
9
+ "CumSum",
10
+ "Div",
11
+ "Constant",
12
+ "ReduceMean",
13
+ "ScatterND",
14
+ "Gather",
15
+ "Equal",
16
+ "Shape",
17
+ "Slice",
18
+ "Concat",
19
+ "Where",
20
+ "ConstantOfShape",
21
+ "Cast",
22
+ "Less",
23
+ "Not",
24
+ "Unsqueeze",
25
+ "Mul",
26
+ "Reshape",
27
+ "Tanh",
28
+ "Expand",
29
+ "Add",
30
+ "Range",
31
+ "Transpose",
32
+ "Sqrt",
33
+ "Softmax",
34
+ "Pow",
35
+ "Or"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_model_merged": {
40
+ "op_types": [
41
+ "Sub",
42
+ "MatMul",
43
+ "CumSum",
44
+ "Div",
45
+ "Constant",
46
+ "ReduceMean",
47
+ "ScatterND",
48
+ "Gather",
49
+ "Equal",
50
+ "Shape",
51
+ "Slice",
52
+ "Concat",
53
+ "Where",
54
+ "ConstantOfShape",
55
+ "Cast",
56
+ "Less",
57
+ "If",
58
+ "Not",
59
+ "Unsqueeze",
60
+ "Mul",
61
+ "Reshape",
62
+ "Tanh",
63
+ "Expand",
64
+ "Add",
65
+ "Range",
66
+ "Transpose",
67
+ "Sqrt",
68
+ "Softmax",
69
+ "Pow",
70
+ "Or"
71
+ ],
72
+ "weight_type": "QInt8"
73
+ },
74
+ "decoder_with_past_model": {
75
+ "op_types": [
76
+ "Sub",
77
+ "MatMul",
78
+ "CumSum",
79
+ "Div",
80
+ "Constant",
81
+ "ReduceMean",
82
+ "Gather",
83
+ "Equal",
84
+ "Shape",
85
+ "Concat",
86
+ "Where",
87
+ "ConstantOfShape",
88
+ "Cast",
89
+ "Not",
90
+ "Unsqueeze",
91
+ "Mul",
92
+ "Reshape",
93
+ "Tanh",
94
+ "Expand",
95
+ "Add",
96
+ "Transpose",
97
+ "Sqrt",
98
+ "Softmax",
99
+ "Pow"
100
+ ],
101
+ "weight_type": "QInt8"
102
+ }
103
+ }
104
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
3
+ size 14500471
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }