Hugging Face's logo

Xenova
/
WizardCoder-1B-V1.0

Text Generation
Transformers.js
ONNX
gpt_bigcode
Model card Files Community
Xenova HF staff commited on
Commit
dc6e503
•
1 Parent(s): f01f992

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +3 -0
  2. added_tokens.json +3 -0
  3. config.json +38 -0
  4. generation_config.json +6 -0
  5. merges.txt +0 -0
  6. onnx/decoder_model.onnx +3 -0
  7. onnx/decoder_model.onnx_data +3 -0
  8. onnx/decoder_model_merged.onnx +3 -0
  9. onnx/decoder_model_merged.onnx_data +3 -0
  10. onnx/decoder_model_merged_quantized.onnx +3 -0
  11. onnx/decoder_model_quantized.onnx +3 -0
  12. onnx/decoder_with_past_model.onnx +3 -0
  13. onnx/decoder_with_past_model.onnx_data +3 -0
  14. onnx/decoder_with_past_model_quantized.onnx +3 -0
  15. quantize_config.json +100 -0
  16. special_tokens_map.json +27 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +32 -0
  19. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 49152
3
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WizardLM/WizardCoder-1B-V1.0",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 2048,
20
+ "n_head": 16,
21
+ "n_inner": 8192,
22
+ "n_layer": 24,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "transformers_version": "4.33.0.dev0",
35
+ "use_cache": false,
36
+ "validate_runner_input": true,
37
+ "vocab_size": 49153
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.33.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26694b5c55b14d02deb11b982e66f526e7b54873d7956445fc4c3be6ad59a04d
3
+ size 67546220
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6253284e87546fd7b71cd8edcc17fc9746650c1b0740d4f83b4d44a26e8a6b
3
+ size 4548837376
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44eb9bd6f360806a76956e5c30747c7f2cb34f44ae7c588ce48f58b33c383fca
3
+ size 135080792
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6253284e87546fd7b71cd8edcc17fc9746650c1b0740d4f83b4d44a26e8a6b
3
+ size 4548837376
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ae4b0a165cd7ebbd0f85d927ccf4442c7708ee40093d5d7c7860923b5537c6
3
+ size 1274416101
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21055e3b7a8c72b60d02e746475cf1b7639c1f4b1418594190e93a2fb8a15890
3
+ size 1206635985
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdea6acd5648a2e53c65c946ed695eb99a5956f3986f28e9e7844d9544718602
3
+ size 67557861
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6253284e87546fd7b71cd8edcc17fc9746650c1b0740d4f83b4d44a26e8a6b
3
+ size 4548837376
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:048d3cc8b17a2e44bb6997a541cdb02b55317ca974312999a4b83a47ded66df1
3
+ size 1206646507
quantize_config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Sqrt",
8
+ "Mul",
9
+ "Equal",
10
+ "Squeeze",
11
+ "And",
12
+ "Gather",
13
+ "Slice",
14
+ "Sub",
15
+ "Split",
16
+ "ReduceMean",
17
+ "Concat",
18
+ "Transpose",
19
+ "Shape",
20
+ "CumSum",
21
+ "Constant",
22
+ "Div",
23
+ "Cast",
24
+ "Reshape",
25
+ "Where",
26
+ "Tanh",
27
+ "Softmax",
28
+ "MatMul",
29
+ "ConstantOfShape",
30
+ "Add",
31
+ "Unsqueeze",
32
+ "Pow"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_model_merged": {
37
+ "op_types": [
38
+ "Sqrt",
39
+ "Mul",
40
+ "Equal",
41
+ "Squeeze",
42
+ "And",
43
+ "If",
44
+ "Gather",
45
+ "Slice",
46
+ "Sub",
47
+ "Split",
48
+ "ReduceMean",
49
+ "Concat",
50
+ "Transpose",
51
+ "Shape",
52
+ "CumSum",
53
+ "Constant",
54
+ "Div",
55
+ "Cast",
56
+ "Reshape",
57
+ "Where",
58
+ "Tanh",
59
+ "Softmax",
60
+ "MatMul",
61
+ "ConstantOfShape",
62
+ "Add",
63
+ "Unsqueeze",
64
+ "Pow"
65
+ ],
66
+ "weight_type": "QInt8"
67
+ },
68
+ "decoder_with_past_model": {
69
+ "op_types": [
70
+ "Sqrt",
71
+ "Mul",
72
+ "Squeeze",
73
+ "Equal",
74
+ "And",
75
+ "Gather",
76
+ "Slice",
77
+ "Sub",
78
+ "Split",
79
+ "ReduceMean",
80
+ "Concat",
81
+ "Transpose",
82
+ "Shape",
83
+ "CumSum",
84
+ "Constant",
85
+ "Div",
86
+ "Cast",
87
+ "Reshape",
88
+ "Where",
89
+ "Tanh",
90
+ "Softmax",
91
+ "MatMul",
92
+ "ConstantOfShape",
93
+ "Add",
94
+ "Unsqueeze",
95
+ "Pow"
96
+ ],
97
+ "weight_type": "QInt8"
98
+ }
99
+ }
100
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": "<|endoftext|>",
24
+ "eos_token": "<|endoftext|>",
25
+ "pad_token": "[PAD]",
26
+ "unk_token": "<|endoftext|>"
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "additional_special_tokens": [
4
+ "<|endoftext|>",
5
+ "<fim_prefix>",
6
+ "<fim_middle>",
7
+ "<fim_suffix>",
8
+ "<fim_pad>",
9
+ "<filename>",
10
+ "<gh_stars>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<empty_output>",
19
+ "<commit_before>",
20
+ "<commit_msg>",
21
+ "<commit_after>",
22
+ "<reponame>"
23
+ ],
24
+ "bos_token": "<|endoftext|>",
25
+ "clean_up_tokenization_spaces": true,
26
+ "eos_token": "<|endoftext|>",
27
+ "model_max_length": 8192,
28
+ "padding_side": "right",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "<|endoftext|>",
31
+ "vocab_size": 49152
32
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff