Update all references to canonical models (#29001)

* Script & Manual edition

* Update

docs/source/zh/main_classes/deepspeed.md

@@ -178,7 +178,7 @@ deepspeed --num_gpus=2 your_program.py <normal cl args> --deepspeed ds_config.js
 ```bash
 deepspeed examples/pytorch/translation/run_translation.py \
 --deepspeed tests/deepspeed/ds_config_zero3.json \
---model_name_or_path t5-small --per_device_train_batch_size 1 \
+--model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \
 --output_dir output_dir --overwrite_output_dir --fp16 \
 --do_train --max_train_samples 500 --num_train_epochs 1 \
 --dataset_name wmt16 --dataset_config "ro-en" \
@@ -201,7 +201,7 @@ deepspeed examples/pytorch/translation/run_translation.py \
 ```bash
 deepspeed --num_gpus=1 examples/pytorch/translation/run_translation.py \
 --deepspeed tests/deepspeed/ds_config_zero2.json \
---model_name_or_path t5-small --per_device_train_batch_size 1 \
+--model_name_or_path google-t5/t5-small --per_device_train_batch_size 1 \
 --output_dir output_dir --overwrite_output_dir --fp16 \
 --do_train --max_train_samples 500 --num_train_epochs 1 \
 --dataset_name wmt16 --dataset_config "ro-en" \
@@ -1628,7 +1628,7 @@ from transformers import T5ForConditionalGeneration, T5Config
 import deepspeed
 
 with deepspeed.zero.Init():
-    config = T5Config.from_pretrained("t5-small")
+    config = T5Config.from_pretrained("google-t5/t5-small")
     model = T5ForConditionalGeneration(config)
 ```
 
@@ -1640,7 +1640,7 @@ with deepspeed.zero.Init():
 from transformers import AutoModel, Trainer, TrainingArguments
 
 training_args = TrainingArguments(..., deepspeed=ds_config)
-model = AutoModel.from_pretrained("t5-small")
+model = AutoModel.from_pretrained("google-t5/t5-small")
 trainer = Trainer(model=model, args=training_args, ...)
 ```
 
@@ -1690,7 +1690,7 @@ deepspeed --num_gpus=2 your_program.py <normal cl args> --do_eval --deepspeed ds
 ```bash
 deepspeed examples/pytorch/translation/run_translation.py \
 --deepspeed tests/deepspeed/ds_config_zero3.json \
---model_name_or_path t5-small --output_dir output_dir \
+--model_name_or_path google-t5/t5-small --output_dir output_dir \
 --do_eval --max_eval_samples 50 --warmup_steps 50  \
 --max_source_length 128 --val_max_target_length 128 \
 --overwrite_output_dir --per_device_eval_batch_size 4 \
@@ -1870,7 +1870,7 @@ import deepspeed
 ds_config = {...}  # deepspeed config object or path to the file
 # must run before instantiating the model to detect zero 3
 dschf = HfDeepSpeedConfig(ds_config)  # keep this object alive
-model = AutoModel.from_pretrained("gpt2")
+model = AutoModel.from_pretrained("openai-community/gpt2")
 engine = deepspeed.initialize(model=model, config_params=ds_config, ...)
 ```
 
@@ -1884,7 +1884,7 @@ import deepspeed
 ds_config = {...}  # deepspeed config object or path to the file
 # must run before instantiating the model to detect zero 3
 dschf = HfDeepSpeedConfig(ds_config)  # keep this object alive
-config = AutoConfig.from_pretrained("gpt2")
+config = AutoConfig.from_pretrained("openai-community/gpt2")
 model = AutoModel.from_config(config)
 engine = deepspeed.initialize(model=model, config_params=ds_config, ...)
 ```

docs/source/zh/main_classes/output.md

@@ -24,8 +24,8 @@ rendered properly in your Markdown viewer.
 from transformers import BertTokenizer, BertForSequenceClassification
 import torch
 
-tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
-model = BertForSequenceClassification.from_pretrained("bert-base-uncased")
+tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased")
+model = BertForSequenceClassification.from_pretrained("google-bert/bert-base-uncased")
 
 inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
 labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1

docs/source/zh/main_classes/pipelines.md

@@ -39,7 +39,7 @@ pipelines是使用模型进行推理的一种简单方法。这些pipelines是
 如果您想使用 [hub](https://huggingface.co) 上的特定模型，可以忽略任务，如果hub上的模型已经定义了该任务：
 
 ```python
->>> pipe = pipeline(model="roberta-large-mnli")
+>>> pipe = pipeline(model="FacebookAI/roberta-large-mnli")
 >>> pipe("This restaurant is awesome")
 [{'label': 'NEUTRAL', 'score': 0.7313136458396912}]
 ```

docs/source/zh/main_classes/trainer.md

@@ -462,7 +462,7 @@ sudo ln -s /usr/bin/g++-7  /usr/local/cuda-10.2/bin/g++
 export TASK_NAME=mrpc
 
 python examples/pytorch/text-classification/run_glue.py \
-  --model_name_or_path bert-base-cased \
+  --model_name_or_path google-bert/bert-base-cased \
   --task_name $TASK_NAME \
   --do_train \
   --do_eval \
@@ -597,7 +597,7 @@ cd transformers
 
 accelerate launch \
 ./examples/pytorch/text-classification/run_glue.py \
---model_name_or_path bert-base-cased \
+--model_name_or_path google-bert/bert-base-cased \
 --task_name $TASK_NAME \
 --do_train \
 --do_eval \
@@ -622,7 +622,7 @@ accelerate launch --num_processes=2 \
 --fsdp_sharding_strategy=1 \
 --fsdp_state_dict_type=FULL_STATE_DICT \
 ./examples/pytorch/text-classification/run_glue.py
---model_name_or_path bert-base-cased \
+--model_name_or_path google-bert/bert-base-cased \
 --task_name $TASK_NAME \
 --do_train \
 --do_eval \