Update migration guide - generation config (#42470)

* update nit

* ig doc builder is complaining about this unclosed code block?

* ?

* ??

* then let's just not have another embedded code block in python block

Author: zucchini-nlp

MIGRATION_GUIDE_V5.md

@@ -330,6 +330,7 @@ model_4bit = AutoModelForCausalLM.from_pretrained(
 - It is no longer possible to load a config class from a URL file. Configs must be loaded from either a local path or a repo on the Hub. See [#42383](https://github.com/huggingface/transformers/pull/42383).
 - All parameters for configuring model's rotary embedding are now stored under `mode.rope_parameters`, including the `rope_theta` and `rope_type`. Model's `config.rope_parameters` is a simple dictionaty in most cases, and can also be a nested dict in special cases (i.e. Gemma3 and ModernBert) with different rope parameterization for each layer type. See [#39847](https://github.com/huggingface/transformers/pull/39847)
 - Qwen-VL family configuration is in a nested format and trying to access keys directly will throw an error (e.g. `config.vocab_size`). Users are expected to access keys from their respective sub-configs (`config.text_config.vocab_size`).
+- Configurations of non-generative models (any model that doesn't call `model.generate()`) will no longer have a `generation_config` and `model.config.generation_config` will throw an attribute error.
 
 ## Processing
 

src/transformers/models/cohere/tokenization_cohere.py

@@ -280,8 +280,8 @@ def apply_tool_use_template(
         Examples:
 
         ```python
-        tokenizer = CohereTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01")
-        tools = [
+        >> tokenizer = CohereTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01")
+        >> tools = [
             {
                 "name": "internet_search",
                 "description": "Returns a list of relevant document snippets for a textual query retrieved from the internet",
@@ -299,16 +299,15 @@ def apply_tool_use_template(
                 "parameter_definitions": {},
             },
         ]
-        conversation = [
+        >> conversation = [
             {"role": "user", "content": "Whats the biggest penguin in the world?"},
         ]
-        # Render the prompt, ready for user to inspect, or for input into the model
-        prompt = tokenizer.apply_tool_use_template(conversation, tools=tools, tokenize=False, add_generation_prompt=True)
-        print(prompt)
+        >> # Render the prompt, ready for user to inspect, or for input into the model
+        >> prompt = tokenizer.apply_tool_use_template(conversation, tools=tools, tokenize=False, add_generation_prompt=True)
+        >> print(prompt)
         >> inputs = tokenizer.encode(grounded_generation_prompt, add_special_tokens=False, return_tensors='pt')
         >> outputs = model.generate(inputs, max_new_tokens=128)
         >> print(tokenizer.decode(outputs[0]))
-        Action: ```json
         [
             {
                 "tool_name": "internet_search",