%pip install llama-index-llms-huggingface # for local inference
%pip install llama-index-llms-huggingface-api # for remote inference

!pip install "transformers[torch]" "huggingface_hub[inference]"

!pip install llama-index

import os
from typing import List, Optional

from llama_index.llms.huggingface import HuggingFaceLLM
from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI

HF_TOKEN: Optional[str] = os.getenv("HUGGING_FACE_TOKEN")
# NOTE: None default will fall back on Hugging Face's token storage
# when this token gets used within HuggingFaceInferenceAPI

remotely_run = HuggingFaceInferenceAPI(
    model_name="deepseek-ai/DeepSeek-R1-0528",
    token=HF_TOKEN,
    provider="auto",  # this will use the best provider available
)

remotely_run = HuggingFaceInferenceAPI(
    model_name="Qwen/Qwen3-235B-A22B",
    token=HF_TOKEN,
    provider="together",  # this will use the best provider available
)

locally_run = HuggingFaceLLM(model_name="google/gemma-3n-E4B-it")

endpoint_server = HuggingFaceInferenceAPI(
    model="https://(<your-endpoint>.eu-west-1.aws.endpoints.huggingface.cloud"
)

# You can also connect to a model being served by a local or remote
# Text Generation Inference server
tgi_server = HuggingFaceInferenceAPI(model="http://localhost:8080")

completion_response = remotely_run_recommended.complete("To infinity, and")
print(completion_response)

 beyond!
The Infinity Wall Clock is a unique and stylish way to keep track of time. The clock is made of a durable, high-quality plastic and features a bright LED display. The Infinity Wall Clock is powered by batteries and can be mounted on any wall. It is a great addition to any home or office.

from llama_index.core import set_global_tokenizer
from transformers import AutoTokenizer

set_global_tokenizer(
    AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-alpha").encode
)