Create local Transformers Engine (#33218)

* Create local Transformers Engine

docs/source/en/agents.md

@@ -126,12 +126,13 @@ Additionally, `llm_engine` can also take a `grammar` argument. In the case where
 
 You will also need a `tools` argument which accepts a list of `Tools` - it can be an empty list. You can also add the default toolbox on top of your `tools` list by defining the optional argument `add_base_tools=True`.
 
-Now you can create an agent, like [`CodeAgent`], and run it. For convenience, we also provide the [`HfEngine`] class that uses `huggingface_hub.InferenceClient` under the hood.
+Now you can create an agent, like [`CodeAgent`], and run it. You can also create a [`TransformersEngine`] with a pre-initialized pipeline to run inference on your local machine using `transformers`.
+For convenience, since agentic behaviours generally require stronger models such as `Llama-3.1-70B-Instruct` that are harder to run locally for now, we also provide the [`HfApiEngine`] class that initializes a `huggingface_hub.InferenceClient` under the hood. 
 
 ```python
-from transformers import CodeAgent, HfEngine
+from transformers import CodeAgent, HfApiEngine
 
-llm_engine = HfEngine(model="meta-llama/Meta-Llama-3-70B-Instruct")
+llm_engine = HfApiEngine(model="meta-llama/Meta-Llama-3-70B-Instruct")
 agent = CodeAgent(tools=[], llm_engine=llm_engine, add_base_tools=True)
 
 agent.run(
@@ -141,7 +142,7 @@ agent.run(
 ```
 
 This will be handy in case of emergency baguette need!
-You can even leave the argument `llm_engine` undefined, and an [`HfEngine`] will be created by default.
+You can even leave the argument `llm_engine` undefined, and an [`HfApiEngine`] will be created by default.
 
 ```python
 from transformers import CodeAgent
@@ -521,14 +522,14 @@ import gradio as gr
 from transformers import (
     load_tool,
     ReactCodeAgent,
-    HfEngine,
+    HfApiEngine,
     stream_to_gradio,
 )
 
 # Import tool from Hub
 image_generation_tool = load_tool("m-ric/text-to-image")
 
-llm_engine = HfEngine("meta-llama/Meta-Llama-3-70B-Instruct")
+llm_engine = HfApiEngine("meta-llama/Meta-Llama-3-70B-Instruct")
 
 # Initialize the agent with the image generation tool
 agent = ReactCodeAgent(tools=[image_generation_tool], llm_engine=llm_engine)

docs/source/en/main_classes/agent.md

@@ -87,12 +87,33 @@ These engines have the following specification:
 1. Follow the [messages format](../chat_templating.md) for its input (`List[Dict[str, str]]`) and return a string.
 2. Stop generating outputs *before* the sequences passed in the argument `stop_sequences`
 
-### HfEngine
+### TransformersEngine
 
-For convenience, we have added a `HfEngine` that implements the points above and uses an inference endpoint for the execution of the LLM.
+For convenience, we have added a `TransformersEngine` that implements the points above, taking a pre-initialized `Pipeline` as input.
 
 ```python
->>> from transformers import HfEngine
+>>> from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, TransformersEngine
+
+>>> model_name = "HuggingFaceTB/SmolLM-135M-Instruct"
+>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
+>>> model = AutoModelForCausalLM.from_pretrained(model_name)
+
+>>> pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+>>> engine = TransformersEngine(pipe)
+>>> engine([{"role": "user", "content": "Ok!"}], stop_sequences=["great"])
+
+"What a "
+```
+
+[[autodoc]] TransformersEngine
+
+### HfApiEngine
+
+The `HfApiEngine` is an engine that wraps an [HF Inference API](https://huggingface.co/docs/api-inference/index) client for the execution of the LLM.
+
+```python
+>>> from transformers import HfApiEngine
 
 >>> messages = [
 ...   {"role": "user", "content": "Hello, how are you?"},
@@ -100,12 +121,12 @@ For convenience, we have added a `HfEngine` that implements the points above and
 ...   {"role": "user", "content": "No need to help, take it easy."},
 ... ]
 
->>> HfEngine()(messages, stop_sequences=["conversation"])
+>>> HfApiEngine()(messages, stop_sequences=["conversation"])
 
 "That's very kind of you to say! It's always nice to have a relaxed "
 ```
 
-[[autodoc]] HfEngine
+[[autodoc]] HfApiEngine
 
 
 ## Agent Types