michaelfeil commited on
Commit
ea79024
1 Parent(s): df6304f

Upload Salesforce/codegen-2B-multi ctranslate fp16 weights

Browse files
.gitattributes CHANGED
@@ -1,28 +1,22 @@
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
  *.tflite filter=lfs diff=lfs merge=lfs -text
@@ -30,5 +24,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.wasm filter=lfs diff=lfs merge=lfs -text
31
  *.xz filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
- *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
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
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
  *.bz2 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
  *.model filter=lfs diff=lfs merge=lfs -text
12
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
 
13
  *.onnx filter=lfs diff=lfs merge=lfs -text
14
  *.ot filter=lfs diff=lfs merge=lfs -text
15
  *.parquet filter=lfs diff=lfs merge=lfs -text
16
  *.pb filter=lfs diff=lfs merge=lfs -text
 
 
17
  *.pt filter=lfs diff=lfs merge=lfs -text
18
  *.pth filter=lfs diff=lfs merge=lfs -text
19
  *.rar filter=lfs diff=lfs merge=lfs -text
 
20
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
  *.tar.* filter=lfs diff=lfs merge=lfs -text
22
  *.tflite filter=lfs diff=lfs merge=lfs -text
 
24
  *.wasm filter=lfs diff=lfs merge=lfs -text
25
  *.xz filter=lfs diff=lfs merge=lfs -text
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - ctranslate2
4
+ - int8
5
+ - float16
6
+
7
+ license: bsd-3-clause
8
+ ---
9
+ # # Fast-Inference with Ctranslate2
10
+ Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.
11
+
12
+ quantized version of [Salesforce/codegen-2B-multi](https://huggingface.co/Salesforce/codegen-2B-multi)
13
+ ```bash
14
+ pip install hf-hub-ctranslate2>=2.0.8
15
+ ```
16
+ Converted on 2023-05-21 using
17
+ ```
18
+ ct2-transformers-converter --model Salesforce/codegen-2B-multi --output_dir /home/michael/tmp-ct2fast-codegen-2B-multi --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json vocab.json special_tokens_map.json added_tokens.json .gitattributes --quantization float16
19
+ ```
20
+
21
+ Checkpoint compatible to [ctranslate2>=3.13.0](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2>=2.0.6](https://github.com/michaelfeil/hf-hub-ctranslate2)
22
+ - `compute_type=int8_float16` for `device="cuda"`
23
+ - `compute_type=int8` for `device="cpu"`
24
+
25
+ ```python
26
+ from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
27
+ from transformers import AutoTokenizer
28
+
29
+ model_name = "michaelfeil/ct2fast-codegen-2B-multi"
30
+ # use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
31
+ model = GeneratorCT2fromHfHub(
32
+ # load in int8 on CUDA
33
+ model_name_or_path=model_name,
34
+ device="cuda",
35
+ compute_type="int8_float16",
36
+ # tokenizer=AutoTokenizer.from_pretrained("Salesforce/codegen-2B-multi")
37
+ )
38
+ outputs = model.generate(
39
+ text=["def print_hello_world():", "def hello_name(name:"],
40
+ max_length=64
41
+ )
42
+ print(outputs)
43
+ ```
44
+
45
+ # Licence and other remarks:
46
+ This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.
47
+
48
+ # Original description
49
+
50
+ tags:
51
+ - ctranslate2
52
+ - int8
53
+ - float16
54
+
55
+ # CodeGen (CodeGen-Multi 2B)
56
+
57
+ ## Model description
58
+
59
+ CodeGen is a family of autoregressive language models for **program synthesis** from the paper: [A Conversational Paradigm for Program Synthesis](https://arxiv.org/abs/2203.13474) by Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong. The models are originally released in [this repository](https://github.com/salesforce/CodeGen), under 3 pre-training data variants (`NL`, `Multi`, `Mono`) and 4 model size variants (`350M`, `2B`, `6B`, `16B`).
60
+
61
+ The checkpoint included in this repository is denoted as **CodeGen-Multi 2B** in the paper, where "Multi" means the model is initialized with *CodeGen-NL 2B* and further pre-trained on a dataset of multiple programming languages, and "2B" refers to the number of trainable parameters.
62
+
63
+ ## Training data
64
+
65
+ This checkpoint (CodeGen-Multi 2B) was firstly initialized with *CodeGen-NL 2B*, and then pre-trained on [BigQuery](https://console.cloud.google.com/marketplace/details/github/github-repos), a large-scale dataset of multiple programming languages from GitHub repositories. The data consists of 119.2B tokens and includes C, C++, Go, Java, JavaScript, and Python.
66
+
67
+ ## Training procedure
68
+
69
+ CodeGen was trained using cross-entropy loss to maximize the likelihood of sequential inputs.
70
+ The family of models are trained using multiple TPU-v4-512 by Google, leveraging data and model parallelism.
71
+ See Section 2.3 of the [paper](https://arxiv.org/abs/2203.13474) for more details.
72
+
73
+ ## Evaluation results
74
+
75
+ We evaluate our models on two code generation benchmark: HumanEval and MTPB. Please refer to the [paper](https://arxiv.org/abs/2203.13474) for more details.
76
+
77
+
78
+ ## Intended Use and Limitations
79
+
80
+ As an autoregressive language model, CodeGen is capable of extracting features from given natural language and programming language texts, and calculating the likelihood of them.
81
+ However, the model is intended for and best at **program synthesis**, that is, generating executable code given English prompts, where the prompts should be in the form of a comment string. The model can complete partially-generated code as well.
82
+
83
+ ## How to use
84
+
85
+ This model can be easily loaded using the `AutoModelForCausalLM` functionality:
86
+
87
+ ```python
88
+ from transformers import AutoTokenizer, AutoModelForCausalLM
89
+ tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-2B-multi")
90
+ model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-2B-multi")
91
+
92
+ text = "def hello_world():"
93
+ input_ids = tokenizer(text, return_tensors="pt").input_ids
94
+
95
+ generated_ids = model.generate(input_ids, max_length=128)
96
+ print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
97
+ ```
98
+
99
+ ## BibTeX entry and citation info
100
+
101
+ ```bibtex
102
+ @article{Nijkamp2022ACP,
103
+ title={A Conversational Paradigm for Program Synthesis},
104
+ author={Nijkamp, Erik and Pang, Bo and Hayashi, Hiroaki and Tu, Lifu and Wang, Huan and Zhou, Yingbo and Savarese, Silvio and Xiong, Caiming},
105
+ journal={arXiv preprint},
106
+ year={2022}
107
+ }
108
+ ```
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {" ": 50280, " ": 50284, " ": 50262, " ": 50266, "\t\t\t\t\t\t\t": 50289, " ": 50264, " ": 50279, " ": 50281, "\t\t\t\t\t\t\t\t\t": 50287, " ": 50286, "\t\t\t": 50293, " ": 50261, " ": 50282, " ": 50283, " ": 50269, " ": 50273, " ": 50271, "\t\t\t\t\t\t\t\t": 50288, " ": 50285, " ": 50276, "\t\t\t\t\t\t": 50290, "\t\t\t\t\t": 50291, " ": 50263, " ": 50278, " ": 50258, " ": 50270, " ": 50259, " ": 50272, " ": 50274, " ": 50267, " ": 50268, "\t\t": 50294, " ": 50257, " ": 50277, "\t\t\t\t": 50292, " ": 50260, " ": 50265, " ": 50275}
config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbec668a976e522b7998f3c46c7aed577a3ea4d4ac115fcfb6c3d260e2075a4
3
+ size 5558730208
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "CodeGenTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
vocabulary.txt ADDED
The diff for this file is too large to render. See raw diff