Hugging Face's logo

Xenova
/
tiny_starcoder_py

Text Generation
Transformers.js
ONNX
gpt_bigcode
Model card Files Community
1
Xenova HF staff commited on
Commit
141c21d
•
1 Parent(s): 5f570e7

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. config.json +38 -0
  2. generation_config.json +6 -0
  3. merges.txt +0 -0
  4. onnx/decoder_model.onnx +3 -0
  5. onnx/decoder_model_merged.onnx +3 -0
  6. onnx/decoder_model_merged_quantized.onnx +3 -0
  7. onnx/decoder_model_quantized.onnx +3 -0
  8. onnx/decoder_with_past_model.onnx +3 -0
  9. onnx/decoder_with_past_model_quantized.onnx +3 -0
  10. quantize_config.json +100 -0
  11. special_tokens_map.json +26 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +31 -0
  14. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/tiny_starcoder_py",
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": 768,
20
+ "n_head": 12,
21
+ "n_inner": 3072,
22
+ "n_layer": 20,
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": "4.32.0.dev0",
35
+ "use_cache": true,
36
+ "validate_runner_input": true,
37
+ "vocab_size": 49152
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": "4.32.0.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 sha256:086035920a278bf46877997575337c46cad5ffc746367a188da646df349f0cda
3
+ size 875006955
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e852014acc486bff04ac66ea20bb8e7a8b4b755d608efc404352439f586cbe20
3
+ size 942448642
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cf095deb2100ff660c231e8bff39af026c8848ad10ffaf57e89749c1e1c3e5
3
+ size 338500911
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4910505d4c3186dd789d1d3dfc3e834eca200549185f43beb09bb3bd3e5edd49
3
+ size 270851872
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f2798827a11f474b4e8a98f02182b66982c6f934fc959d2b2b74d016afbbd0
3
+ size 875014307
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc393be238b4a5bd3337c1165a8b17cd63a907a847a6b38b539f8cfe39c6be3
3
+ size 270860829
quantize_config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "CumSum",
8
+ "ConstantOfShape",
9
+ "Cast",
10
+ "Gather",
11
+ "ReduceMean",
12
+ "Reshape",
13
+ "Concat",
14
+ "Div",
15
+ "Squeeze",
16
+ "Unsqueeze",
17
+ "Equal",
18
+ "Pow",
19
+ "Constant",
20
+ "MatMul",
21
+ "Sub",
22
+ "And",
23
+ "Slice",
24
+ "Tanh",
25
+ "Add",
26
+ "Split",
27
+ "Mul",
28
+ "Shape",
29
+ "Softmax",
30
+ "Sqrt",
31
+ "Where",
32
+ "Transpose"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_model": {
37
+ "op_types": [
38
+ "CumSum",
39
+ "ConstantOfShape",
40
+ "Cast",
41
+ "Gather",
42
+ "ReduceMean",
43
+ "Reshape",
44
+ "Concat",
45
+ "Div",
46
+ "Squeeze",
47
+ "Unsqueeze",
48
+ "Equal",
49
+ "Pow",
50
+ "Constant",
51
+ "MatMul",
52
+ "Sub",
53
+ "And",
54
+ "Slice",
55
+ "Tanh",
56
+ "Add",
57
+ "Split",
58
+ "Mul",
59
+ "Shape",
60
+ "Softmax",
61
+ "Sqrt",
62
+ "Where",
63
+ "Transpose"
64
+ ],
65
+ "weight_type": "QInt8"
66
+ },
67
+ "decoder_model_merged": {
68
+ "op_types": [
69
+ "CumSum",
70
+ "ConstantOfShape",
71
+ "Cast",
72
+ "Gather",
73
+ "ReduceMean",
74
+ "Reshape",
75
+ "Concat",
76
+ "Div",
77
+ "Squeeze",
78
+ "If",
79
+ "Unsqueeze",
80
+ "Equal",
81
+ "Pow",
82
+ "Constant",
83
+ "MatMul",
84
+ "Sub",
85
+ "And",
86
+ "Slice",
87
+ "Tanh",
88
+ "Add",
89
+ "Split",
90
+ "Mul",
91
+ "Shape",
92
+ "Softmax",
93
+ "Sqrt",
94
+ "Where",
95
+ "Transpose"
96
+ ],
97
+ "weight_type": "QInt8"
98
+ }
99
+ }
100
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": "<|endoftext|>"
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000000000000019884624838656,
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "<|endoftext|>",
30
+ "vocab_size": 49152
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff