Hugging Face

import requests

API_URL = "https://api-inference.huggingface.co/models/google/flan-t5-large"
headers = {"Authorization": "Bearer ******"}

def query(payload):
	response = requests.post(API_URL, headers=headers, json=payload)
	return response.json()
	
output = query({
	"inputs": "The answer to the universe is",
})

from langchain_community.llms.huggingface_hub import HuggingFaceHub
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
import os

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "******"

repo_id = "google/flan-t5-large" 

template = """
Question: {sentence}
"""

prompt = PromptTemplate.from_template(template)

llm = HuggingFaceHub(
    repo_id=repo_id, model_kwargs={"temperature": 0.5, "max_length": 64}
)
llm_chain = LLMChain(prompt=prompt, llm=llm)

print(llm_chain.invoke({
    "sentence": "What is the capital of France?"
}))

pip install huggingface_hub

pip install transformers

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/phi-2")
pipe.save_pretrained("model/phi-2")

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("model/phi-2", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("model/phi-2", trust_remote_code=True)

inputs = tokenizer('''def print_prime(n):
   """
   Print all primes between 1 and n
   """''', return_tensors="pt", return_attention_mask=False)

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)