Xenova HF staff commited on
Commit
aa993b7
1 Parent(s): 8ba459c

Upload folder using huggingface_hub

Browse files
.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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-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
+ "skip_bias_add": true,
25
+ "skip_bias_add_qkv": false,
26
+ "slow_but_exact": false,
27
+ "transformers_version": "4.30.2",
28
+ "unk_token_id": 0,
29
+ "use_cache": true,
30
+ "vocab_size": 250880
31
+ }
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": "4.30.2"
7
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c318453eb4bdb7205e9a33c398de2e9db0e663513279fb065bccf4b00aa973ac
3
+ size 708438
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046f1802b6053dc36e20f2058b1dca128cd9164cd37d34495962afa1f21ca102
3
+ size 3264462848
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae962cef1ef0779118e8e9aa24fa93ec79db2b4a283ee9473d5ed99303ca2e7
3
+ size 1399393
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046f1802b6053dc36e20f2058b1dca128cd9164cd37d34495962afa1f21ca102
3
+ size 3264462848
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d4d5e6cb5ca13b52fbe996e058870f5ae8016cfe8f17fcce7f2ee5805d8d52
3
+ size 821504874
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83014d55c5fa9fc9264040513b9b7bd5eff1d9d4da78d66acfae8410c222efa
3
+ size 820477030
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78714ec76dae1951e26d8823252c78ab621ef2d449fb59d19bcd95d9c7ddd498
3
+ size 714961
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046f1802b6053dc36e20f2058b1dca128cd9164cd37d34495962afa1f21ca102
3
+ size 3264462848
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f981dcad0360bd9da6f48d95f457fd0a9590c29d4ef9fb9114b95e42f125328f
3
+ size 820479158
quant_config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "CumSum",
8
+ "Not",
9
+ "Reshape",
10
+ "Sub",
11
+ "ReduceMean",
12
+ "Transpose",
13
+ "Equal",
14
+ "Range",
15
+ "Softmax",
16
+ "Pow",
17
+ "Mul",
18
+ "Concat",
19
+ "ConstantOfShape",
20
+ "Constant",
21
+ "Gather",
22
+ "Cast",
23
+ "Div",
24
+ "ScatterND",
25
+ "MatMul",
26
+ "Or",
27
+ "Add",
28
+ "Expand",
29
+ "Less",
30
+ "Unsqueeze",
31
+ "Shape",
32
+ "Sqrt",
33
+ "Tanh",
34
+ "Where",
35
+ "Slice"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_with_past_model": {
40
+ "op_types": [
41
+ "CumSum",
42
+ "Not",
43
+ "Reshape",
44
+ "Sub",
45
+ "ReduceMean",
46
+ "Transpose",
47
+ "Equal",
48
+ "Softmax",
49
+ "Pow",
50
+ "Mul",
51
+ "Concat",
52
+ "ConstantOfShape",
53
+ "Constant",
54
+ "Gather",
55
+ "Cast",
56
+ "Div",
57
+ "MatMul",
58
+ "Add",
59
+ "Expand",
60
+ "Unsqueeze",
61
+ "Shape",
62
+ "Sqrt",
63
+ "Tanh",
64
+ "Where"
65
+ ],
66
+ "weight_type": "QInt8"
67
+ },
68
+ "decoder_model_merged": {
69
+ "op_types": [
70
+ "CumSum",
71
+ "Not",
72
+ "Reshape",
73
+ "Sub",
74
+ "ReduceMean",
75
+ "If",
76
+ "Transpose",
77
+ "Equal",
78
+ "Range",
79
+ "Softmax",
80
+ "Pow",
81
+ "Mul",
82
+ "Concat",
83
+ "ConstantOfShape",
84
+ "Constant",
85
+ "Gather",
86
+ "Cast",
87
+ "Div",
88
+ "ScatterND",
89
+ "MatMul",
90
+ "Or",
91
+ "Add",
92
+ "Expand",
93
+ "Less",
94
+ "Unsqueeze",
95
+ "Shape",
96
+ "Sqrt",
97
+ "Tanh",
98
+ "Where",
99
+ "Slice"
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
+ }