初始化项目，由ModelHub XC社区提供模型

Model: lbox/lcube-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+*.wasm 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

README.md

@@ -0,0 +1,42 @@
+## How to use 
+```python
+import transformers
+
+model = transformers.GPT2LMHeadModel.from_pretrained("lbox/lcube-base")
+tokenizer = transformers.AutoTokenizer.from_pretrained(
+    "lbox/lcube-base",
+    bos_token="[BOS]",
+    unk_token="[UNK]",
+    pad_token="[PAD]",
+    mask_token="[MASK]",
+)
+
+text = "피고인은 불상지에 있는 커피숍에서, 피해자 B으로부터"
+model_inputs = tokenizer(text,
+                         max_length=1024,
+                         padding=True,
+                         truncation=True,
+                         return_tensors='pt')
+out = model.generate(
+    model_inputs["input_ids"], 
+    max_new_tokens=150,
+    pad_token_id=tokenizer.pad_token_id,
+    use_cache=True,
+    repetition_penalty=1.2,
+    top_k=5,
+    top_p=0.9,
+    temperature=1,
+    num_beams=2,
+)
+tokenizer.batch_decode(out)
+```
+
+For more information please visit <https://github.com/lbox-kr/lbox_open>.
+
+
+
+## Licensing Information
+
+Copyright 2022-present LBox Co. Ltd.
+
+Licensed under the CC BY-NC-ND 4.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../data/models/backbones/lbox-open-gpt-small-50k",
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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,
+  "tokenizer_class": "GPT2TokenizerFast",
+  "transformers_version": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d08cf700e0fc48032e1eca29900baaa215a9fef5eeff405f41a15c0459dd384
+size 510545769

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}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb59f51564a9579f132034e47858196d0eeb7197c52ed2dcc828a90960e0bed
+size 498079848

tokenizer_config.json

@@ -0,0 +1 @@
+{"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": true, "errors": "replace", "special_tokens_map_file": "../data/models/backbones/lbox-open-gpt-small-50k/special_tokens_map.json", "name_or_path": "../data/models/backbones/lbox-open-gpt-small-50k", "tokenizer_class": "GPT2Tokenizer"}