Hugging Face's logo

eaten
/
codet5p-2b-finetuned-code-generation

Text2Text Generation
Transformers
PyTorch
codet5p
custom_code
Model card Files Community
eaten commited on
Commit
6899b7c
•
1 Parent(s): d94ec22

model and petf files

Browse files
Files changed (20) hide show
  1. added_tokens.json +40 -0
  2. config.json +195 -0
  3. fine_tuned_model/README.md +10 -0
  4. fine_tuned_model/adapter_config.json +21 -0
  5. fine_tuned_model/adapter_model.bin +3 -0
  6. fine_tuned_model/added_tokens.json +40 -0
  7. fine_tuned_model/merges.txt +0 -0
  8. fine_tuned_model/special_tokens_map.json +6 -0
  9. fine_tuned_model/tokenizer.json +0 -0
  10. fine_tuned_model/tokenizer_config.json +9 -0
  11. fine_tuned_model/training_args.bin +3 -0
  12. fine_tuned_model/vocab.json +0 -0
  13. generation_config.json +7 -0
  14. merges.txt +0 -0
  15. pytorch_model.bin +3 -0
  16. special_tokens_map.json +6 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +9 -0
  19. training_args.bin +3 -0
  20. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "48dd1d613db426104ce52c0bb2dfd19352173fac",
3
+ "_name_or_path": "Salesforce/codet5p-2b",
4
+ "architectures": [
5
+ "CodeT5pEncoderDecoderModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "Salesforce/codet5p-2b--configuration_codet5p.CodeT5pConfig",
9
+ "AutoModel": "Salesforce/codet5p-2b--modeling_codet5p.CodeGenModel",
10
+ "AutoModelForSeq2SeqLM": "Salesforce/codet5p-2b--modeling_codet5p.CodeT5pEncoderDecoderModel"
11
+ },
12
+ "decoder": {
13
+ "_name_or_path": "codet5p-2b-decoder",
14
+ "activation_function": "gelu_new",
15
+ "add_cross_attention": true,
16
+ "architectures": [
17
+ "CodeT5pForCausalLM"
18
+ ],
19
+ "attn_pdrop": 0.0,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 1,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": 50256,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "embd_pdrop": 0.0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 50256,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "gradient_checkpointing": false,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "is_decoder": true,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "layer_norm_epsilon": 1e-05,
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "min_length": 0,
52
+ "model_type": "codet5p_module",
53
+ "n_ctx": 2048,
54
+ "n_embd": 2560,
55
+ "n_head": 32,
56
+ "n_inner": null,
57
+ "n_layer": 32,
58
+ "n_positions": 2048,
59
+ "no_repeat_ngram_size": 0,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": null,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "resid_pdrop": 0.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "rotary_dim": 64,
76
+ "scale_attn_weights": true,
77
+ "sep_token_id": null,
78
+ "summary_activation": null,
79
+ "summary_first_dropout": 0.1,
80
+ "summary_proj_to_labels": true,
81
+ "summary_type": "cls_index",
82
+ "summary_use_proj": true,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": false,
89
+ "tokenizer_class": "GPT2Tokenizer",
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": "float16",
93
+ "torchscript": false,
94
+ "transformers_version": "4.31.0",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": false,
97
+ "use_cache": true,
98
+ "vocab_size": 51200
99
+ },
100
+ "decoder_start_token_id": 50256,
101
+ "encoder": {
102
+ "_name_or_path": "codet5p-350m-encoder",
103
+ "activation_function": "gelu_new",
104
+ "add_cross_attention": false,
105
+ "architectures": [
106
+ "CodeT5pModel"
107
+ ],
108
+ "attn_pdrop": 0.0,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 1,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": 50256,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "embd_pdrop": 0.0,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": 50256,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "gradient_checkpointing": false,
126
+ "id2label": {
127
+ "0": "LABEL_0",
128
+ "1": "LABEL_1"
129
+ },
130
+ "initializer_range": 0.02,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_epsilon": 1e-05,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "model_type": "codet5p_module",
142
+ "n_ctx": 2048,
143
+ "n_embd": 1024,
144
+ "n_head": 16,
145
+ "n_inner": null,
146
+ "n_layer": 20,
147
+ "n_positions": 2048,
148
+ "no_repeat_ngram_size": 0,
149
+ "num_beam_groups": 1,
150
+ "num_beams": 1,
151
+ "num_return_sequences": 1,
152
+ "output_attentions": false,
153
+ "output_hidden_states": false,
154
+ "output_scores": false,
155
+ "pad_token_id": null,
156
+ "prefix": null,
157
+ "problem_type": null,
158
+ "pruned_heads": {},
159
+ "remove_invalid_values": false,
160
+ "repetition_penalty": 1.0,
161
+ "resid_pdrop": 0.0,
162
+ "return_dict": true,
163
+ "return_dict_in_generate": false,
164
+ "rotary_dim": 32,
165
+ "scale_attn_weights": true,
166
+ "sep_token_id": null,
167
+ "summary_activation": null,
168
+ "summary_first_dropout": 0.1,
169
+ "summary_proj_to_labels": true,
170
+ "summary_type": "cls_index",
171
+ "summary_use_proj": true,
172
+ "suppress_tokens": null,
173
+ "task_specific_params": null,
174
+ "temperature": 1.0,
175
+ "tf_legacy_loss": false,
176
+ "tie_encoder_decoder": false,
177
+ "tie_word_embeddings": false,
178
+ "tokenizer_class": "GPT2Tokenizer",
179
+ "top_k": 50,
180
+ "top_p": 1.0,
181
+ "torch_dtype": "float16",
182
+ "torchscript": false,
183
+ "transformers_version": "4.31.0",
184
+ "typical_p": 1.0,
185
+ "use_bfloat16": false,
186
+ "use_cache": true,
187
+ "vocab_size": 51200
188
+ },
189
+ "gradient_checkpointing": true,
190
+ "is_encoder_decoder": true,
191
+ "model_type": "codet5p",
192
+ "pad_token_id": 50256,
193
+ "torch_dtype": "float16",
194
+ "transformers_version": null
195
+ }
fine_tuned_model/README.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+ - PEFT 0.4.0
9
+
10
+ - PEFT 0.4.0
fine_tuned_model/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "Salesforce/codet5p-2b",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "SEQ_2_SEQ_LM"
21
+ }
fine_tuned_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d15a24ee38389184d175bf03d4ffb1bdbf865232e542a54b517a4e135c8c70
3
+ size 13390965
fine_tuned_model/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
fine_tuned_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
fine_tuned_model/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
fine_tuned_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
fine_tuned_model/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "tokenizer_class": "CodeGenTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
fine_tuned_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192a267bf4b9a6d9876e0358acf6ebe30d71a688940e206b3e2578b6726fda3a
3
+ size 4155
fine_tuned_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.31.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8aca992e39adbcabf6181b1b283711e5c462d451bae72abb15f822d3dd1924b
3
+ size 6447315341
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "tokenizer_class": "CodeGenTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e14ef180b9ca513a3915e1ca094bce728bc630a112be3b8554ad713d486a4e
3
+ size 4155
vocab.json ADDED
The diff for this file is too large to render. See raw diff