初始化项目，由ModelHub XC社区提供模型

Model: iic/nlp_gpt2_text-generation_english-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,32 @@
+*.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
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+tasks:
+- text-generation
+
+model-type:
+- gpt
+
+domain:
+- nlp
+
+frameworks:
+- pytorch
+
+backbone:
+- transformer
+
+containers:
+
+metrics:
+- BLEU-4
+- Rouge-L
+
+license: Apache License 2.0
+
+language: 
+- ch
+
+tags:
+- transformer
+- AliceMind
+- volume:abs/2005.14165
+
+---
+
+# GPT-2文本生成模型介绍
+GPT-2 是一个 transformer 模型，以自我监督的方式在大量英语数据集上进行预训练。 这意味着它仅在原始文本上进行了预训练，没有以任何方式进行标记，，并通过自动过程从这些文本生成输入和标签。 也可以说，它被训练来猜测句子中的下一个单词。
+
+对于训练而言，输入是一定长度的连续文本序列，目标是相同的序列，向右移动一个标记（单词或单词片段）。 该模型在内部使用掩码机制来确保对第 i 个 token 的预测仅使用从 1 到 i 的输入，不包括后续的内容。
+
+通过这种方式，该模型学习了输入语料的内部表示，然后可用于提取对下游任务有用的特征。 这是 GPT-2 的 base 版本，有 124M 参数。
+
+
+## 模型描述
+GPT-2模型使用 Transformer 的 Decoder 结构，并对 Transformer Decoder 进行了一些改动，原本的 Decoder 包含了两个 Multi-Head Attention 结构，GPT-2只保留了 Self Mask Multi-Head Attention，利用常规的语言建模优化，从左到右的自回归预训练。
+
+## 期望模型使用方式以及适用范围
+本模型主要用于多种场景输入的生成和续写。比如用户可以自行尝试输入各种内容，然后让模型去回答、续写或者根据指令回复
+
+### 如何使用
+在安装完成MaaS-lib之后即可使用GPT-2的text-generation的能力
+
+#### 代码范例
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+text_generator = pipeline(Tasks.text_generation, model='damo/nlp_gpt2_text-generation_english-base', model_revision='v1.0.0', external_engine_for_llm=False)
+result_zh = text_generator('My name is Teven and I am')
+print(result_zh['text'])
+```
+
+### 模型局限性以及可能的偏差
+模型在大量无标注的英文数据集上训练，有可能产生一些偏差，请用户自行评测后决定如何使用。
+
+## 训练数据介绍
+本模型采用无监督数据对GPT-2进行训练，其中无监督数据为公开可下载的语料
+
+## 模型训练流程
+
+本模型暂不支持在 ModelScope 进行训练
+
+### 相关论文以及引用信息
+如果GPT-2模型对您有帮助，请您引用该模型的相关文章：
+```
+@article{radford2019language,
+  title={Language Models are Unsupervised Multitask Learners},
+  author={Radford, Alec and Wu, Jeff and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
+  year={2019}
+}
+```
+

config.json

@@ -0,0 +1,31 @@
+{
+  "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_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "vocab_size": 50257
+}

configuration.json

@@ -0,0 +1,85 @@
+{
+    "task": "text-generation",
+    "framework": "pytorch",
+    "preprocessor": {
+        "type": "text-gen-tokenizer",
+        "padding": false
+    },
+    "model": {
+        "type": "text-generation",
+        "do_sample": true,
+        "top_k": 20,
+        "top_p": 0.95,
+        "max_length": 100,
+        "repetition_penalty": 1,
+        "bos_token_id": 50256,
+        "eos_token_id": 50256,
+        "pad_token_id": 0,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "length_penalty": 1.0,
+        "diversity_penalty": 0.0,
+        "early_stopping": false,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "return_dict_in_generate": false,
+        "is_encoder_decoder": false,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "min_length": 0,
+        "remove_invalid_values": false,
+        "temperature": 1.0,
+        "shared_embedding": true,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "typical_p": 1.0,
+        "backbone": {
+            "type": "gpt2",
+            "prefix": "transformer",
+            "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_layer": 12,
+            "n_positions": 1024,
+            "resid_pdrop": 0.1,
+            "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
+              }
+            },
+            "vocab_size": 50257
+        },
+        "head": {
+            "type": "text-generation",
+            "hidden_dropout_prob": 0.1,
+            "vocab_size": 50257,
+            "hidden_size": 768
+        }
+    },
+    "pipeline": {
+        "type": "text-generation"
+    }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35ad3f171c8768c601373f812de50b2d2d36fd09e130619283e4d0a6bc52e69
+size 548139073