Transformers cli clean command (#37657)

* transformers-cli -> transformers

* Chat command works with positional argument

* update doc references to transformers-cli

* doc headers

* deepspeed

---------

Co-authored-by: Joao Gante <joao@huggingface.co>

docs/source/en/model_doc/bert.md

@@ -81,10 +81,10 @@ print(f"The predicted token is: {predicted_token}")
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers-cli run --task fill-mask --model google-bert/bert-base-uncased --device 0
+echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers run --task fill-mask --model google-bert/bert-base-uncased --device 0
 ```
 
 </hfoption>
@@ -256,4 +256,4 @@ echo -e "Plants create [MASK] through a process known as photosynthesis." | tran
 
 [[autodoc]] models.bert.modeling_tf_bert.TFBertForPreTrainingOutput
 
-[[autodoc]] models.bert.modeling_flax_bert.FlaxBertForPreTrainingOutput
+[[autodoc]] models.bert.modeling_flax_bert.FlaxBertForPreTrainingOutput

docs/source/en/model_doc/code_llama.md

@@ -35,7 +35,7 @@ The example below demonstrates how to generate code with [`Pipeline`], or the [`
 
 <hfoptions id="usage">
 <hfoption id="Pipeline">
-    
+
 ```py
 import torch
 from transformers import pipeline
@@ -76,7 +76,7 @@ prompt = "# Function to calculate the factorial of a number\ndef factorial(n):"
 input_ids = tokenizer(prompt, return_tensors="pt").to("cuda")
 
 output = model.generate(
-    **input_ids, 
+    **input_ids,
     max_new_tokens=256,
     cache_implementation="static"
 )
@@ -92,10 +92,10 @@ print(filled_text)
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
-    
+<hfoption id="transformers CLI">
+
 ```bash
-echo -e "# Function to calculate the factorial of a number\ndef factorial(n):" | transformers-cli run --task text-generation --model meta-llama/CodeLlama-7b-hf --device 0
+echo -e "# Function to calculate the factorial of a number\ndef factorial(n):" | transformers run --task text-generation --model meta-llama/CodeLlama-7b-hf --device 0
 ```
 
 </hfoption>
@@ -146,7 +146,7 @@ visualizer("""def func(a, b):
 - Use the `<FILL_ME>` token where you want your input to be filled. The tokenizer splits this token to create a formatted input string that follows the [original training pattern](https://github.com/facebookresearch/codellama/blob/cb51c14ec761370ba2e2bc351374a79265d0465e/llama/generation.py#L402). This is more robust than preparing the pattern yourself.
     ```py
     from transformers import LlamaForCausalLM, CodeLlamaTokenizer
-    
+
     tokenizer = CodeLlamaTokenizer.from_pretrained("meta-llama/CodeLlama-7b-hf")
     model = LlamaForCausalLM.from_pretrained("meta-llama/CodeLlama-7b-hf")
     PROMPT = '''def remove_non_ascii(s: str) -> str:
@@ -155,7 +155,7 @@ visualizer("""def func(a, b):
     '''
     input_ids = tokenizer(PROMPT, return_tensors="pt")["input_ids"]
     generated_ids = model.generate(input_ids, max_new_tokens=128)
-    
+
     filling = tokenizer.batch_decode(generated_ids[:, input_ids.shape[1]:], skip_special_tokens = True)[0]
     print(PROMPT.replace("<FILL_ME>", filling))
     ```

docs/source/en/model_doc/cohere.md

@@ -49,9 +49,9 @@ model = AutoModelForCausalLM.from_pretrained("CohereForAI/c4ai-command-r-v01", t
 messages = [{"role": "user", "content": "How do plants make energy?"}]
 input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
 output = model.generate(
-    input_ids, 
-    max_new_tokens=100, 
-    do_sample=True, 
+    input_ids,
+    max_new_tokens=100,
+    do_sample=True,
     temperature=0.3,
     cache_implementation="static",
 )
@@ -59,11 +59,11 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
 # pip install -U flash-attn --no-build-isolation
-transformers-cli chat --model_name_or_path CohereForAI/c4ai-command-r-v01 --torch_dtype auto --attn_implementation flash_attention_2
+transformers chat CohereForAI/c4ai-command-r-v01 --torch_dtype auto --attn_implementation flash_attention_2
 ```
 
 </hfoption>
@@ -85,9 +85,9 @@ model = AutoModelForCausalLM.from_pretrained("CohereForAI/c4ai-command-r-v01", t
 messages = [{"role": "user", "content": "How do plants make energy?"}]
 input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
 output = model.generate(
-    input_ids, 
-    max_new_tokens=100, 
-    do_sample=True, 
+    input_ids,
+    max_new_tokens=100,
+    do_sample=True,
     temperature=0.3,
     cache_implementation="static",
 )

docs/source/en/model_doc/distilbert.md

@@ -83,10 +83,10 @@ print(f"Predicted label: {predicted_label}")
 
 </hfoption>
 
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "I love using Hugging Face Transformers!" | transformers-cli run --task text-classification --model distilbert-base-uncased-finetuned-sst-2-english
+echo -e "I love using Hugging Face Transformers!" | transformers run --task text-classification --model distilbert-base-uncased-finetuned-sst-2-english
 ```
 
 </hfoption>
@@ -213,7 +213,3 @@ echo -e "I love using Hugging Face Transformers!" | transformers-cli run --task
 
 </jax>
 </frameworkcontent>
-
-
-
-

docs/source/en/model_doc/electra.md

@@ -45,9 +45,9 @@ import torch
 from transformers import pipeline
 
 classifier = pipeline(
-    task="text-classification", 
-    model="bhadresh-savani/electra-base-emotion", 
-    torch_dtype=torch.float16, 
+    task="text-classification",
+    model="bhadresh-savani/electra-base-emotion",
+    torch_dtype=torch.float16,
     device=0
 )
 classifier("This restaurant has amazing food!")
@@ -64,7 +64,7 @@ tokenizer = AutoTokenizer.from_pretrained(
     "bhadresh-savani/electra-base-emotion",
 )
 model = AutoModelForSequenceClassification.from_pretrained(
-    "bhadresh-savani/electra-base-emotion", 
+    "bhadresh-savani/electra-base-emotion",
     torch_dtype=torch.float16
 )
 inputs = tokenizer("ELECTRA is more efficient than BERT", return_tensors="pt")
@@ -78,10 +78,10 @@ print(f"Predicted label: {predicted_label}")
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "This restaurant has amazing food." | transformers-cli run --task text-classification --model bhadresh-savani/electra-base-emotion --device 0
+echo -e "This restaurant has amazing food." | transformers run --task text-classification --model bhadresh-savani/electra-base-emotion --device 0
 ```
 
 </hfoption>
@@ -96,12 +96,12 @@ echo -e "This restaurant has amazing food." | transformers-cli run --task text-c
 
     ```py
     # Example of properly handling padding with attention masks
-    inputs = tokenizer(["Short text", "This is a much longer text that needs padding"], 
-                    padding=True, 
+    inputs = tokenizer(["Short text", "This is a much longer text that needs padding"],
+                    padding=True,
                     return_tensors="pt")
     outputs = model(**inputs)  # automatically uses the attention_mask
     ```
-    
+
 - When using the discriminator for a downstream task, you can load it into any of the ELECTRA model classes ([`ElectraForSequenceClassification`], [`ElectraForTokenClassification`], etc.).
 
 ## ElectraConfig

docs/source/en/model_doc/falcon.md

@@ -41,7 +41,7 @@ import torch
 from transformers import pipeline
 
 pipeline = pipeline(
-    task="text-generation", 
+    task="text-generation",
     model="tiiuae/falcon-7b-instruct",
     torch_dtype=torch.bfloat16,
     device=0
@@ -76,11 +76,11 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
 # pip install -U flash-attn --no-build-isolation
-transformers-cli chat --model_name_or_path tiiuae/falcon-7b-instruct --torch_dtype auto --attn_implementation flash_attention_2 --device 0
+transformers chat tiiuae/falcon-7b-instruct --torch_dtype auto --attn_implementation flash_attention_2 --device 0
 ```
 
 </hfoption>
@@ -150,4 +150,4 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ## FalconForQuestionAnswering
 
 [[autodoc]] FalconForQuestionAnswering
-    - forward
+    - forward

docs/source/en/model_doc/falcon_mamba.md

@@ -39,7 +39,7 @@ import torch
 from transformers import pipeline
 
 pipeline = pipeline(
-    "text-generation", 
+    "text-generation",
     model="tiiuae/falcon-mamba-7b-instruct",
     torch_dtype=torch.bfloat16,
     device=0
@@ -73,10 +73,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-transformers-cli chat --model_name_or_path tiiuae/falcon-mamba-7b-instruct --torch_dtype auto --device 0
+transformers chat tiiuae/falcon-mamba-7b-instruct --torch_dtype auto --device 0
 ```
 
 </hfoption>

docs/source/en/model_doc/gemma.md

@@ -80,10 +80,10 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "LLMs generate text through a process known as" | transformers-cli run --task text-generation --model google/gemma-2b --device 0
+echo -e "LLMs generate text through a process known as" | transformers run --task text-generation --model google/gemma-2b --device 0
 ```
 
 </hfoption>
@@ -114,8 +114,8 @@ model = AutoModelForCausalLM.from_pretrained(
 input_text = "LLMs generate text through a process known as."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 outputs = model.generate(
-    **input_ids, 
-    max_new_tokens=50, 
+    **input_ids,
+    max_new_tokens=50,
     cache_implementation="static"
 )
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
@@ -127,7 +127,7 @@ Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/bl
 from transformers.utils.attention_visualizer import AttentionMaskVisualizer
 
 visualizer = AttentionMaskVisualizer("google/gemma-2b")
-visualizer("LLMs generate text through a process known as") 
+visualizer("LLMs generate text through a process known as")
 ```
 
 <div class="flex justify-center">

docs/source/en/model_doc/gemma2.md

@@ -58,7 +58,7 @@ pipe("Explain quantum computing simply. ", max_new_tokens=50)
 
 </hfoption>
 <hfoption id="AutoModel">
-    
+
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -80,16 +80,16 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```
-echo -e "Explain quantum computing simply." | transformers-cli run --task text-generation --model google/gemma-2-2b --device 0
+echo -e "Explain quantum computing simply." | transformers run --task text-generation --model google/gemma-2-2b --device 0
 ```
 </hfoption>
 </hfoptions>
 
 Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the [Quantization](../quantization/overview) overview for more available quantization backends.
-	
+
 The example below uses [bitsandbytes](../quantization/bitsandbytes) to only quantize the weights to int4.
 
 ```python
@@ -118,7 +118,7 @@ Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/bl
 ```python
 from transformers.utils.attention_visualizer import AttentionMaskVisualizer
 visualizer = AttentionMaskVisualizer("google/gemma-2b")
-visualizer("You are an assistant. Make sure you print me") 
+visualizer("You are an assistant. Make sure you print me")
 ```
 
 <div class="flex justify-center">
@@ -137,7 +137,7 @@ visualizer("You are an assistant. Make sure you print me")
 
     inputs = tokenizer(text="My name is Gemma", return_tensors="pt")
     max_generated_length = inputs.input_ids.shape[1] + 10
-    past_key_values = HybridCache(config=model.config, max_batch_size=1, 
+    past_key_values = HybridCache(config=model.config, max_batch_size=1,
     max_cache_len=max_generated_length, device=model.device, dtype=model.dtype)
     outputs = model(**inputs, past_key_values=past_key_values, use_cache=True)
     ```

docs/source/en/model_doc/gemma3.md

@@ -99,10 +99,10 @@ print(processor.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "Plants create energy through a process known as" | transformers-cli run --task text-generation --model google/gemma-3-1b-pt --device 0
+echo -e "Plants create energy through a process known as" | transformers run --task text-generation --model google/gemma-3-1b-pt --device 0
 ```
 
 </hfoption>

docs/source/en/model_doc/gpt2.md

@@ -64,10 +64,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "Hello, I'm a language model" | transformers-cli run --task text-generation --model openai-community/gpt2 --device 0
+echo -e "Hello, I'm a language model" | transformers run --task text-generation --model openai-community/gpt2 --device 0
 ```
 
 </hfoption>
@@ -82,16 +82,16 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, pipeline
 
 quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,  
-    bnb_4bit_quant_type="nf4",  
-    bnb_4bit_compute_dtype="float16",  
-    bnb_4bit_use_double_quant=True 
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype="float16",
+    bnb_4bit_use_double_quant=True
 )
 
 model = AutoModelForCausalLM.from_pretrained(
     "openai-community/gpt2-xl",
     quantization_config=quantization_config,
-    device_map="auto"  
+    device_map="auto"
 )
 
 tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2-xl")

docs/source/en/model_doc/jamba.md

@@ -75,10 +75,10 @@ output = model.generate(**input_ids, cache_implementation="static")
 print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "Plants create energy through a process known as" | transformers-cli run --task text-generation --model ai21labs/AI21-Jamba-Mini-1.6 --device 0
+echo -e "Plants create energy through a process known as" | transformers run --task text-generation --model ai21labs/AI21-Jamba-Mini-1.6 --device 0
 ```
 
 </hfoption>

docs/source/en/model_doc/llama.md

@@ -74,10 +74,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "Plants create energy through a process known as" | transformers-cli run --task text-generation --model huggyllama/llama-7b --device 0
+echo -e "Plants create energy through a process known as" | transformers run --task text-generation --model huggyllama/llama-7b --device 0
 ```
 
 </hfoption>

docs/source/en/model_doc/llama2.md

@@ -74,10 +74,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-transformers-cli chat --model_name_or_path meta-llama/Llama-2-7b-chat-hf --torch_dtype auto --attn_implementation flash_attention_2
+transformers chat meta-llama/Llama-2-7b-chat-hf --torch_dtype auto --attn_implementation flash_attention_2
 ```
 
 </hfoption>
@@ -175,4 +175,3 @@ visualizer("Plants create energy through a process known as")
 
 [[autodoc]] LlamaForSequenceClassification
     - forward
-

docs/source/en/model_doc/longformer.md

@@ -76,10 +76,10 @@ tokenizer.decode(predictions).split()
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "San Francisco 49ers cornerback Shawntae Spencer will miss the rest of the <mask> with a torn ligament in his left knee." | transformers-cli run --task fill-mask --model allenai/longformer-base-4096 --device 0
+echo -e "San Francisco 49ers cornerback Shawntae Spencer will miss the rest of the <mask> with a torn ligament in his left knee." | transformers run --task fill-mask --model allenai/longformer-base-4096 --device 0
 ```
 
 </hfoption>
@@ -147,42 +147,42 @@ echo -e "San Francisco 49ers cornerback Shawntae Spencer will miss the rest of t
 
 ## LongformerForMaskedLM
 
-[[autodoc]] LongformerForMaskedLM 
+[[autodoc]] LongformerForMaskedLM
     - forward
 
 ## LongformerForSequenceClassification
 
-[[autodoc]] LongformerForSequenceClassification 
+[[autodoc]] LongformerForSequenceClassification
     - forward
 
 ## LongformerForMultipleChoice
 
-[[autodoc]] LongformerForMultipleChoice 
+[[autodoc]] LongformerForMultipleChoice
     - forward
 
 ## LongformerForTokenClassification
 
-[[autodoc]] LongformerForTokenClassification 
+[[autodoc]] LongformerForTokenClassification
     - forward
 
 ## LongformerForQuestionAnswering
 
-[[autodoc]] LongformerForQuestionAnswering 
+[[autodoc]] LongformerForQuestionAnswering
     - forward
 
 ## TFLongformerModel
 
-[[autodoc]] TFLongformerModel    
+[[autodoc]] TFLongformerModel
     - call
 
 ## TFLongformerForMaskedLM
 
-[[autodoc]] TFLongformerForMaskedLM 
+[[autodoc]] TFLongformerForMaskedLM
     - call
 
 ## TFLongformerForQuestionAnswering
 
-[[autodoc]] TFLongformerForQuestionAnswering 
+[[autodoc]] TFLongformerForQuestionAnswering
     - call
 
 ## TFLongformerForSequenceClassification
@@ -192,10 +192,10 @@ echo -e "San Francisco 49ers cornerback Shawntae Spencer will miss the rest of t
 
 ## TFLongformerForTokenClassification
 
-[[autodoc]] TFLongformerForTokenClassification 
+[[autodoc]] TFLongformerForTokenClassification
     - call
 
 ## TFLongformerForMultipleChoice
 
-[[autodoc]] TFLongformerForMultipleChoice 
+[[autodoc]] TFLongformerForMultipleChoice
     - call

docs/source/en/model_doc/mistral.md

@@ -27,7 +27,7 @@ rendered properly in your Markdown viewer.
 
 # Mistral
 
-[Mistral](https://huggingface.co/papers/2310.06825) is a 7B parameter language model, available as a pretrained and instruction-tuned variant, focused on balancing 
+[Mistral](https://huggingface.co/papers/2310.06825) is a 7B parameter language model, available as a pretrained and instruction-tuned variant, focused on balancing
 the scaling costs of large models with performance and efficient inference. This model uses sliding window attention (SWA) trained with a 8K context length and a fixed cache size to handle longer sequences more effectively. Grouped-query attention (GQA) speeds up inference and reduces memory requirements. Mistral also features a byte-fallback BPE tokenizer to improve token handling and efficiency by ensuring characters are never mapped to out-of-vocabulary tokens.
 
 You can find all the original Mistral checkpoints under the [Mistral AI_](https://huggingface.co/mistralai) organization.
@@ -78,10 +78,10 @@ The example below demonstrates how to chat with [`Pipeline`] or the [`AutoModel`
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```python
-echo -e "My favorite condiment is" | transformers-cli chat --model_name_or_path mistralai/Mistral-7B-v0.3 --torch_dtype auto --device 0 --attn_implementation flash_attention_2
+echo -e "My favorite condiment is" | transformers chat mistralai/Mistral-7B-v0.3 --torch_dtype auto --device 0 --attn_implementation flash_attention_2
 ```
 
 </hfoption>

docs/source/en/model_doc/mobilebert.md

@@ -76,10 +76,10 @@ print(f"The predicted token is: {predicted_token}")
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "The capital of France is [MASK]." | transformers-cli run --task fill-mask --model google/mobilebert-uncased --device 0
+echo -e "The capital of France is [MASK]." | transformers run --task fill-mask --model google/mobilebert-uncased --device 0
 ```
 
 </hfoption>

docs/source/en/model_doc/modernbert.md

@@ -79,10 +79,10 @@ print(f"The predicted token is: {predicted_token}")
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers-cli run --task fill-mask --model answerdotai/ModernBERT-base --device 0
+echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers run --task fill-mask --model answerdotai/ModernBERT-base --device 0
 ```
 
 </hfoption>

docs/source/en/model_doc/openai-gpt.md

@@ -70,10 +70,10 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "The future of AI is" | transformers-cli run --task text-generation --model openai-community/openai-gpt --device 0
+echo -e "The future of AI is" | transformers run --task text-generation --model openai-community/openai-gpt --device 0
 
 ```
 </hfoption>

docs/source/en/model_doc/phi.md

@@ -65,10 +65,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "'''def print_prime(n): """ Print all primes between 1 and n"""'''" | transformers-cli run --task text-classification --model microsoft/phi-1.5 --device 0
+echo -e "'''def print_prime(n): """ Print all primes between 1 and n"""'''" | transformers run --task text-classification --model microsoft/phi-1.5 --device 0
 ```
 
 </hfoption>
@@ -102,7 +102,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
     ```py
     import torch
     from transformers import AutoTokenizer, AutoModelForCausalLM
-    
+
     tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1")
     model = AutoModelForCausalLM.from_pretrained(
         "microsoft/phi-1",
@@ -110,12 +110,12 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
         device_map="auto",
         trust_remote_code=True,
         attn_implementation="sdpa")
-    
+
     input_ids = tokenizer('''def print_prime(n):
        """
        Print all primes between 1 and n
        """''', return_tensors="pt").to("cuda")
-    
+
     output = model.generate(**input_ids, cache_implementation="static")
     print(tokenizer.decode(output[0], skip_special_tokens=True))
     ```

docs/source/en/model_doc/qwen2.md

@@ -64,7 +64,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model = AutoModelForCausalLM.from_pretrained(
     "Qwen/Qwen2-1.5B-Instruct",
-    torch_dtype=torch.bfloat16, 
+    torch_dtype=torch.bfloat16,
     device_map="auto",
     attn_implementation="sdpa"
 )
@@ -86,10 +86,10 @@ generated_ids = model.generate(
     model_inputs.input_ids,
     cache_implementation="static",
     max_new_tokens=512,
-    do_sample=True, 
-    temperature=0.7, 
-    top_k=50,        
-    top_p=0.95       
+    do_sample=True,
+    temperature=0.7,
+    top_k=50,
+    top_p=0.95
 )
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
@@ -100,11 +100,11 @@ print(response)
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
 # pip install -U flash-attn --no-build-isolation
-transformers-cli chat --model_name_or_path Qwen/Qwen2-7B-Instruct --torch_dtype auto --attn_implementation flash_attention_2 --device 0
+transformers chat Qwen/Qwen2-7B-Instruct --torch_dtype auto --attn_implementation flash_attention_2 --device 0
 ```
 
 </hfoption>
@@ -121,21 +121,21 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.bfloat16, 
-    bnb_4bit_quant_type="nf4",             
-    bnb_4bit_use_double_quant=True,       
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_use_double_quant=True,
 )
 
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B") 
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B")
 model = AutoModelForCausalLM.from_pretrained(
     "Qwen/Qwen2-7B",
     torch_dtype=torch.bfloat16,
     device_map="auto",
     quantization_config=quantization_config,
-    attn_implementation="flash_attention_2" 
+    attn_implementation="flash_attention_2"
 )
 
-inputs = tokenizer("The Qwen2 model family is", return_tensors="pt").to("cuda") 
+inputs = tokenizer("The Qwen2 model family is", return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=100)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```

docs/source/en/model_doc/t5.md

@@ -75,10 +75,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 </hfoption>
-<hfoption id="transformers-cli">
+<hfoption id="transformers CLI">
 
 ```bash
-echo -e "translate English to French: The weather is nice today." | transformers-cli run --task text2text-generation --model google-t5/t5-base --device 0
+echo -e "translate English to French: The weather is nice today." | transformers run --task text2text-generation --model google-t5/t5-base --device 0
 ```
 
 </hfoption>