senwu commited on
Commit
f14c7c5
0 Parent(s):

initial commit

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ inference:
4
+ parameters:
5
+ do_sample: false
6
+ max_length: 200
7
+ widget:
8
+ - text: "CREATE TABLE stadium (\n stadium_id number,\n location text,\n name text,\n capacity number,\n)\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many stadiums in total?\n\nSELECT"
9
+ example_title: "Number stadiums"
10
+ - text: "CREATE TABLE work_orders ( ID NUMBER, CREATED_AT TEXT, COST FLOAT, INVOICE_AMOUNT FLOAT, IS_DUE BOOLEAN, IS_OPEN BOOLEAN, IS_OVERDUE BOOLEAN, COUNTRY_NAME TEXT, )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many work orders are open?\n\nSELECT"
11
+ example_title: "Open work orders"
12
+ - text: "CREATE TABLE stadium ( stadium_id number, location text, name text, capacity number, highest number, lowest number, average number )\n\nCREATE TABLE singer ( singer_id number, name text, country text, song_name text, song_release_year text, age number, is_male others )\n\nCREATE TABLE concert ( concert_id number, concert_name text, theme text, stadium_id text, year text )\n\nCREATE TABLE singer_in_concert ( concert_id number, singer_id text )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- What is the maximum, the average, and the minimum capacity of stadiums ?\n\nSELECT"
13
+ example_title: "Stadium capacity"
14
+ ---
15
+
16
+ # NSQL (NSQL-2B)
17
+
18
+ ## Model Description
19
+
20
+ NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
21
+
22
+ The checkpoint included in this repository is based on [CodeGen-Multi 2B](https://huggingface.co/Salesforce/codegen-2B-multi) from Salesforce and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs.
23
+
24
+ ## Training Data
25
+
26
+ The general SQL queries are the SQL subset from [The Stack](https://huggingface.co/datasets/bigcode/the-stack), containing 1M training samples. The labeled text-to-SQL pairs come from more than 20 public sources across the web from standard datasets. We hold out Spider and GeoQuery datasets for use in evaluation.
27
+
28
+ ## Evaluation Data
29
+
30
+ We evaluate our models on two text-to-SQL benchmarks: Spider and GeoQuery.
31
+
32
+ ## Training Procedure
33
+
34
+ NSQL was trained using cross-entropy loss to maximize the likelihood of sequential inputs. For finetuning on text-to-SQL pairs, we only compute the loss over the SQL portion of the pair. The family of models is trained using 80GB A100s, leveraging data and model parallelism. We pre-trained for 3 epochs and fine-tuned for 10 epochs.
35
+
36
+ ## Intended Use and Limitations
37
+
38
+ The model was designed for text-to-SQL generation tasks from given table schema and natural language prompts. The model works best with the prompt format defined below and outputting `SELECT` queries.
39
+
40
+ ## How to Use
41
+
42
+ Example 1:
43
+
44
+ ```python
45
+ from transformers import AutoTokenizer, AutoModelForCausalLM
46
+ tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-2B")
47
+ model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-2B")
48
+
49
+ text = """CREATE TABLE stadium (
50
+ stadium_id number,
51
+ location text,
52
+ name text,
53
+ capacity number,
54
+ highest number,
55
+ lowest number,
56
+ average number
57
+ )
58
+
59
+ CREATE TABLE singer (
60
+ singer_id number,
61
+ name text,
62
+ country text,
63
+ song_name text,
64
+ song_release_year text,
65
+ age number,
66
+ is_male others
67
+ )
68
+
69
+ CREATE TABLE concert (
70
+ concert_id number,
71
+ concert_name text,
72
+ theme text,
73
+ stadium_id text,
74
+ year text
75
+ )
76
+
77
+ CREATE TABLE singer_in_concert (
78
+ concert_id number,
79
+ singer_id text
80
+ )
81
+
82
+ -- Using valid SQLite, answer the following questions for the tables provided above.
83
+
84
+ -- What is the maximum, the average, and the minimum capacity of stadiums ?
85
+
86
+ SELECT"""
87
+
88
+ input_ids = tokenizer(text, return_tensors="pt").input_ids
89
+
90
+ generated_ids = model.generate(input_ids, max_length=500)
91
+ print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
92
+ ```
93
+
94
+ Example 2:
95
+
96
+ ```python
97
+ from transformers import AutoTokenizer, AutoModelForCausalLM
98
+ tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-2B")
99
+ model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-2B")
100
+
101
+ text = """CREATE TABLE stadium (
102
+ stadium_id number,
103
+ location text,
104
+ name text,
105
+ capacity number,
106
+ )
107
+
108
+ -- Using valid SQLite, answer the following questions for the tables provided above.
109
+
110
+ -- how many stadiums in total?
111
+
112
+ SELECT"""
113
+
114
+ input_ids = tokenizer(text, return_tensors="pt").input_ids
115
+
116
+ generated_ids = model.generate(input_ids, max_length=500)
117
+ print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
118
+ ```
119
+
120
+ Example 3:
121
+
122
+ ```python
123
+ from transformers import AutoTokenizer, AutoModelForCausalLM
124
+ tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-2B")
125
+ model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-2B")
126
+
127
+ text = """CREATE TABLE work_orders (
128
+ ID NUMBER,
129
+ CREATED_AT TEXT,
130
+ COST FLOAT,
131
+ INVOICE_AMOUNT FLOAT,
132
+ IS_DUE BOOLEAN,
133
+ IS_OPEN BOOLEAN,
134
+ IS_OVERDUE BOOLEAN,
135
+ COUNTRY_NAME TEXT,
136
+ )
137
+
138
+ -- Using valid SQLite, answer the following questions for the tables provided above.
139
+
140
+ -- how many work orders are open?
141
+
142
+ SELECT"""
143
+
144
+ input_ids = tokenizer(text, return_tensors="pt").input_ids
145
+
146
+ generated_ids = model.generate(input_ids, max_length=500)
147
+ print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
148
+ ```
149
+
150
+ For more information (e.g., run with your local database), please find examples in [this repository](https://github.com/NumbersStationAI/NSQL).
151
+
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nsql-2B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "CodeGenForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "codegen",
15
+ "n_ctx": 2048,
16
+ "n_embd": 2560,
17
+ "n_head": 32,
18
+ "n_inner": null,
19
+ "n_layer": 32,
20
+ "n_positions": 2048,
21
+ "pad_token_id": 50256,
22
+ "resid_pdrop": 0.0,
23
+ "rotary_dim": 64,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50,
34
+ "temperature": 1.0
35
+ }
36
+ },
37
+ "tie_word_embeddings": false,
38
+ "tokenizer_class": "GPT2Tokenizer",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.28.1",
41
+ "use_cache": true,
42
+ "vocab_size": 51200
43
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.28.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36852e0653d9bca4a61c54ab7a17694a5569234b584bb897b94c1e2919f6a813
3
+ size 10093759237
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754b4d318e29283a48b66634df0341c72352f43d61260b000e8a2cefe03c3448
3
+ size 1157982437
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11134201856.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00002-of-00002.bin",
7
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
8
+ "transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.10.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.11.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.12.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.12.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.13.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.13.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.14.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.14.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.15.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.15.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.16.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.16.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.17.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.17.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.18.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.18.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.19.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.19.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.2.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.20.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.20.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.20.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.21.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.21.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.21.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
142
+ "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
143
+ "transformer.h.22.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.22.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.22.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.23.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.23.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.23.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.24.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.24.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.24.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.25.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.25.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.25.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.26.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.26.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.26.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.27.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.27.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.27.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.28.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.28.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.h.28.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
201
+ "transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
202
+ "transformer.h.28.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
203
+ "transformer.h.28.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
204
+ "transformer.h.28.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
205
+ "transformer.h.28.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
206
+ "transformer.h.29.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
207
+ "transformer.h.29.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "transformer.h.29.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
209
+ "transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
210
+ "transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
211
+ "transformer.h.29.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
212
+ "transformer.h.29.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
213
+ "transformer.h.29.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
214
+ "transformer.h.29.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
215
+ "transformer.h.3.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
216
+ "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
219
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
220
+ "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
221
+ "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
222
+ "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
223
+ "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
224
+ "transformer.h.30.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
225
+ "transformer.h.30.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "transformer.h.30.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "transformer.h.30.ln_1.bias": "pytorch_model-00001-of-00002.bin",
228
+ "transformer.h.30.ln_1.weight": "pytorch_model-00001-of-00002.bin",
229
+ "transformer.h.30.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
230
+ "transformer.h.30.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
231
+ "transformer.h.30.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
232
+ "transformer.h.30.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
233
+ "transformer.h.31.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
234
+ "transformer.h.31.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "transformer.h.31.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
237
+ "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
238
+ "transformer.h.31.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
239
+ "transformer.h.31.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
240
+ "transformer.h.31.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
241
+ "transformer.h.31.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
242
+ "transformer.h.4.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
243
+ "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
246
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
247
+ "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
248
+ "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
249
+ "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
250
+ "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
251
+ "transformer.h.5.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
252
+ "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "transformer.h.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
255
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
256
+ "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
257
+ "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
258
+ "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
259
+ "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
260
+ "transformer.h.6.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
261
+ "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "transformer.h.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
264
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
265
+ "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
266
+ "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
267
+ "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
268
+ "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
269
+ "transformer.h.7.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
270
+ "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "transformer.h.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
273
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
274
+ "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
275
+ "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
276
+ "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
277
+ "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
278
+ "transformer.h.8.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
279
+ "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "transformer.h.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
282
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
283
+ "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
284
+ "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
285
+ "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
286
+ "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
287
+ "transformer.h.9.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
288
+ "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "transformer.h.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
291
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
292
+ "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
293
+ "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
294
+ "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
295
+ "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
296
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
297
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
298
+ "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
299
+ }
300
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
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
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff