初始化项目，由ModelHub XC社区提供模型

Model: shibing624/code-autocomplete-gpt2-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,138 @@
+---
+language: 
+- en
+tags:
+- code
+- autocomplete
+- pytorch
+- en
+license: "apache-2.0"
+---
+
+# GPT2 for Code AutoComplete Model
+code-autocomplete, a code completion plugin for Python.
+
+**code-autocomplete** can automatically complete the code of lines and blocks with GPT2.
+
+## Usage
+
+Open source repo：[code-autocomplete](https://github.com/shibing624/code-autocomplete)，support GPT2 model, usage：
+
+```python
+from autocomplete.gpt2_coder import GPT2Coder
+
+m = GPT2Coder("shibing624/code-autocomplete-gpt2-base")
+print(m.generate('import torch.nn as')[0])
+```
+
+Also, use huggingface/transformers：
+
+*Please use 'GPT2' related functions to load this model!*
+
+```python
+import os
+import torch
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+
+os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = GPT2Tokenizer.from_pretrained("shibing624/code-autocomplete-gpt2-base")
+model = GPT2LMHeadModel.from_pretrained("shibing624/code-autocomplete-gpt2-base")
+model.to(device)
+prompts = [
+    """from torch import nn
+    class LSTM(Module):
+        def __init__(self, *,
+                     n_tokens: int,
+                     embedding_size: int,
+                     hidden_size: int,
+                     n_layers: int):""",
+    """import numpy as np
+    import torch
+    import torch.nn as""",
+    "import java.util.ArrayList",
+    "def factorial(n):",
+]
+for prompt in prompts:
+    input_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors='pt').to(device)
+    outputs = model.generate(input_ids=input_ids,
+                             max_length=64 + len(prompt),
+                             temperature=1.0,
+                             top_k=50,
+                             top_p=0.95,
+                             repetition_penalty=1.0,
+                             do_sample=True,
+                             num_return_sequences=1,
+                             length_penalty=2.0,
+                             early_stopping=True)
+    decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print(decoded)
+    print("=" * 20)
+```
+
+output:
+```shell
+from torch import nn
+    class LSTM(Module):
+        def __init__(self, *,
+                     n_tokens: int,
+                     embedding_size: int,
+                     hidden_size: int,
+                     n_layers: int):
+            self.embedding_size = embedding_size
+====================
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+```
+
+Model files：
+```
+code-autocomplete-gpt2-base
+├── config.json
+├── merges.txt
+├── pytorch_model.bin
+├── special_tokens_map.json
+├── tokenizer_config.json
+└── vocab.json
+```
+
+### Train data
+#### pytorch_awesome projects source code
+
+download [code-autocomplete](https://github.com/shibing624/code-autocomplete),
+```shell
+cd autocomplete
+python create_dataset.py
+```
+
+If you want train code-autocomplete GPT2 model，refer [https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2_coder.py](https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2_coder.py)
+
+
+### About GPT2
+
+Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large
+
+Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in
+[this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
+and first released at [this page](https://openai.com/blog/better-language-models/).
+
+Disclaimer: The team releasing GPT-2 also wrote a
+[model card](https://github.com/openai/gpt-2/blob/master/model_card.md) for their model. Content from this model card
+has been written by the Hugging Face team to complete the information they provided and give specific examples of bias.
+
+
+## Citation
+
+```latex
+@misc{code-autocomplete,
+  author = {Xu Ming},
+  title = {code-autocomplete: Code AutoComplete with GPT model},
+  year = {2022},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  url = {https://github.com/shibing624/code-autocomplete},
+}
+```

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "vocab_size": 50257
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 1.604232376272028
+perplexity = tensor(4.9740)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32b7a78806a0748ad4f55cfa7789632444db3418a62d92169ba8996a667d5fd
+size 510359598

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fcbd85a0ad0914d71af3267556b8b1261d94cb0602a2b15fa1a6588a7f3fd07
+size 510403817

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}