Fix typo in Llama docstrings (#24020)

* Fix typo in Llama docstrings
Signed-off-by: Serge Panev <spanev@nvidia.com>

* Update
Signed-off-by: Serge Panev <spanev@nvidia.com>

* make style
Signed-off-by: Serge Panev <spanev@nvidia.com>

---------
Signed-off-by: Serge Panev <spanev@nvidia.com>

src/transformers/models/llama/modeling_llama.py

@@ -669,13 +669,13 @@ class LlamaForCausalLM(LlamaPreTrainedModel):
         >>> model = LlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
         >>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
 
-        >>> prompt = "Hey, are you consciours? Can you talk to me?"
+        >>> prompt = "Hey, are you conscious? Can you talk to me?"
         >>> inputs = tokenizer(prompt, return_tensors="pt")
 
         >>> # Generate
         >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
         >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-        "Hey, are you consciours? Can you talk to me?\nI'm not consciours, but I can talk to you."
+        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
         ```"""
 
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions

src/transformers/models/open_llama/modeling_open_llama.py

@@ -706,13 +706,13 @@ class OpenLlamaForCausalLM(OpenLlamaPreTrainedModel):
         >>> model = OpenLlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
         >>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
 
-        >>> prompt = "Hey, are you consciours? Can you talk to me?"
+        >>> prompt = "Hey, are you conscious? Can you talk to me?"
         >>> inputs = tokenizer(prompt, return_tensors="pt")
 
         >>> # Generate
         >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
         >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-        "Hey, are you consciours? Can you talk to me?\nI'm not consciours, but I can talk to you."
+        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
         ```"""
 
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions

src/transformers/models/opt/modeling_opt.py

@@ -926,13 +926,13 @@ class OPTForCausalLM(OPTPreTrainedModel):
         >>> model = OPTForCausalLM.from_pretrained("facebook/opt-350m")
         >>> tokenizer = AutoTokenizer.from_pretrained("facebook/opt-350m")
 
-        >>> prompt = "Hey, are you consciours? Can you talk to me?"
+        >>> prompt = "Hey, are you conscious? Can you talk to me?"
         >>> inputs = tokenizer(prompt, return_tensors="pt")
 
         >>> # Generate
         >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
         >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-        "Hey, are you consciours? Can you talk to me?\nI'm not consciours, but I can talk to you."
+        "Hey, are you conscious? Can you talk to me?\nI'm not conscious. I'm just a little bit of a weirdo."
         ```"""
 
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions

src/transformers/models/opt/modeling_tf_opt.py

@@ -54,7 +54,9 @@ _CONFIG_FOR_DOC = "OPTConfig"
 _EXPECTED_OUTPUT_SHAPE = [1, 8, 1024]
 
 # Causal LM output
-_CAUSAL_LM_EXPECTED_OUTPUT = "Hey, are you consciours? Can you talk to me?\nI'm not consciours, but I can talk to you."
+_CAUSAL_LM_EXPECTED_OUTPUT = (
+    "Hey, are you conscious? Can you talk to me?\nI'm not conscious. I'm just a little bit of a weirdo."
+)
 
 LARGE_NEGATIVE = -1e8