updated text encoder files

Signed-off-by: Anhforth <[email protected]>

.gitignore

@@ -0,0 +1,28 @@
+__pycache__
+.idea/
+logs/
+test_tokenizer.py
+samples_text2image/
+generate_contexts/
+venv/
+*__pycache__
+.DS_Store
+.vscode
+*.swo
+*.swp
+*log
+build
+dist
+eazybigmodel.egg-info
+flagai.egg-info
+test_report
+/data/
+/tests/*/data
+checkpoints
+state_dict
+checkpoints*
+vocabs
+tensorboard*
+datasets
+qqp
+glm_large_qqp_pytorch

text_encoder/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "RobertaSeriesModelWithTransformation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "learn_encoder": false,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pooler_fn": "cls",
+  "position_embedding_type": "absolute",
+  "project_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7e5b6bef6737f75d01705be1d59295f5c9d84c10b9715a1610160fb646245d
+size 2242851593

tokenizer/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "/sharefs/baai-mrnd/yzd/test/xlm-roberta-large",
+  "pad_token": "<pad>",
+  "processor_class": "CHCLIPProcess",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}