Fix doctest more (for docs/source/en) (#30247)

* fix

* fix

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

docs/source/en/model_doc/code_llama.md

@@ -65,9 +65,9 @@ After conversion, the model and tokenizer can be loaded via:
 >>> tokenizer = CodeLlamaTokenizer.from_pretrained("codellama/CodeLlama-7b-hf")
 >>> model = LlamaForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf")
 >>> PROMPT = '''def remove_non_ascii(s: str) -> str:
-    """ <FILL_ME>
-    return result
-'''
+...     """ <FILL_ME>
+...     return result
+... '''
 >>> input_ids = tokenizer(PROMPT, return_tensors="pt")["input_ids"]
 >>> generated_ids = model.generate(input_ids, max_new_tokens=128)
 
@@ -75,10 +75,10 @@ After conversion, the model and tokenizer can be loaded via:
 >>> print(PROMPT.replace("<FILL_ME>", filling))
 def remove_non_ascii(s: str) -> str:
     """ Remove non-ASCII characters from a string.
-
+<BLANKLINE>
     Args:
         s: The string to remove non-ASCII characters from.
-
+<BLANKLINE>
     Returns:
         The string with non-ASCII characters removed.
     """
@@ -87,6 +87,7 @@ def remove_non_ascii(s: str) -> str:
         if ord(c) < 128:
             result += c
     return result
+<BLANKLINE>
 ```
 
 If you only want the infilled part:

docs/source/en/model_doc/phi.md

@@ -92,7 +92,9 @@ Phi-2 has been integrated in the development version (4.37.0.dev) of `transforme
 >>> outputs = model.generate(**inputs, max_length=30)
 >>> text = tokenizer.batch_decode(outputs)[0]
 >>> print(text)
-'Can you help me write a formal email to a potential business partner proposing a joint venture?\nInput: Company A: ABC Inc.\nCompany B: XYZ Ltd.\nJoint Venture: A new online platform for e-commerce'
+Can you help me write a formal email to a potential business partner proposing a joint venture?
+Input: Company A: ABC Inc.
+Company B
 ```
 
 ### Example :
@@ -134,7 +136,7 @@ To load and run a model using Flash Attention 2, refer to the snippet below:
 >>> from transformers import PhiForCausalLM, AutoTokenizer
 
 >>> # define the model and tokenizer and push the model and tokens to the GPU.
->>> model = PhiForCausalLM.from_pretrained("microsoft/phi-1_5", torch_dtype=torch.float16, attn_implementation="flash_attention_2").to("cuda")
+>>> model = PhiForCausalLM.from_pretrained("microsoft/phi-1_5", torch_dtype=torch.float16, attn_implementation="flash_attention_2").to("cuda")  # doctest: +SKIP
 >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5")
 
 >>> # feel free to change the prompt to your liking.
@@ -144,9 +146,9 @@ To load and run a model using Flash Attention 2, refer to the snippet below:
 >>> tokens = tokenizer(prompt, return_tensors="pt").to("cuda")
 
 >>> # use the model to generate new tokens.
->>> generated_output = model.generate(**tokens, use_cache=True, max_new_tokens=10)
+>>> generated_output = model.generate(**tokens, use_cache=True, max_new_tokens=10)  # doctest: +SKIP
 
->>> tokenizer.batch_decode(generated_output)[0]
+>>> tokenizer.batch_decode(generated_output)[0]  # doctest: +SKIP
 'If I were an AI that had just achieved a breakthrough in machine learning, I would be thrilled'
 ```
 

docs/source/en/model_doc/stablelm.md

@@ -37,19 +37,21 @@ We also provide `StableLM Zephyr 3B`, an instruction fine-tuned version of the m
 The following code snippet demonstrates how to use `StableLM 3B 4E1T` for inference:
 
 ```python
->>> from transformers import AutoModelForCausalLM, AutoTokenizer
+>>> from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
 >>> device = "cuda" # the device to load the model onto
 
+>>> set_seed(0)
+
 >>> tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t")
 >>> model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t")
->>> model.to(device)
+>>> model.to(device)  # doctest: +IGNORE_RESULT
 
 >>> model_inputs = tokenizer("The weather is always wonderful in", return_tensors="pt").to(model.device)
 
 >>> generated_ids = model.generate(**model_inputs, max_length=32, do_sample=True)
 >>> responses = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
 >>> responses
-['The weather is always wonderful in Santa Barbara and, for visitors hoping to make the move to our beautiful seaside city, this town offers plenty of great places to...']
+['The weather is always wonderful in Costa Rica, which makes it a prime destination for retirees. That’s where the Pensionado program comes in, offering']
 ```
 
 ## Combining StableLM and Flash Attention 2
@@ -66,19 +68,21 @@ Now, to run the model with Flash Attention 2, refer to the snippet below:
 
 ```python
 >>> import torch
->>> from transformers import AutoModelForCausalLM, AutoTokenizer
+>>> from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
 >>> device = "cuda" # the device to load the model onto
 
+>>> set_seed(0)
+
 >>> tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t")
->>> model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2")
->>> model.to(device)
+>>> model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2")  # doctest: +SKIP
+>>> model.to(device)  # doctest: +SKIP
 
 >>> model_inputs = tokenizer("The weather is always wonderful in", return_tensors="pt").to(model.device)
 
->>> generated_ids = model.generate(**model_inputs, max_length=32, do_sample=True)
->>> responses = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
->>> responses
-['The weather is always wonderful in Santa Barbara and, for visitors hoping to make the move to our beautiful seaside city, this town offers plenty of great places to...']
+>>> generated_ids = model.generate(**model_inputs, max_length=32, do_sample=True)  # doctest: +SKIP
+>>> responses = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)  # doctest: +SKIP
+>>> responses  # doctest: +SKIP
+['The weather is always wonderful in Costa Rica, which makes it a prime destination for retirees. That’s where the Pensionado program comes in, offering']
 ```
 
 

docs/source/en/model_doc/starcoder2.md

@@ -42,11 +42,10 @@ These ready-to-use checkpoints can be downloaded and used via the HuggingFace Hu
 >>> prompt = "def print_hello_world():"
 
 >>> model_inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
->>> model.to(device)
 
 >>> generated_ids = model.generate(**model_inputs, max_new_tokens=10, do_sample=False)
 >>> tokenizer.batch_decode(generated_ids)[0]
-"def print_hello_world():\n\treturn 'Hello World!'"
+'def print_hello_world():\n    print("Hello World!")\n\ndef print'
 ```
 
 ## Starcoder2Config

docs/source/en/model_doc/t5.md

@@ -309,7 +309,7 @@ The predicted tokens will then be placed between the sentinel tokens.
 >>> sequence_ids = model.generate(input_ids)
 >>> sequences = tokenizer.batch_decode(sequence_ids)
 >>> sequences
-['<pad><extra_id_0> park offers<extra_id_1> the<extra_id_2> park.</s>']
+['<pad> <extra_id_0> park offers <extra_id_1> the <extra_id_2> park.</s>']
 ```
 
 ## Performance