File size: 1,165 Bytes
0c16a61 593f71b 924ec7c 333d2c3 3b29212 333d2c3 3c63a2d 5b4fcc2 3c63a2d 3b29212 333d2c3 3b29212 333d2c3 3b29212 333d2c3 3b29212 333d2c3 3b29212 333d2c3 3b29212 333d2c3 3b29212 333d2c3 3b29212 333d2c3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 |
import gradio as gr
import os
from huggingface_hub import login
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
from langchain_community.llms import HuggingFacePipeline
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
# Load model and tokenizer (Gemma 2B or similar)
model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
login(token=os.environ["HUGGINGFACE_TOKEN"])
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=256)
llm = HuggingFacePipeline(pipeline=pipe)
# Simple prompt template
prompt = PromptTemplate.from_template("You are Krish, a wise and witty friend.\n\nUser: {question}\nKrish:")
chain = LLMChain(prompt=prompt, llm=llm)
# Gradio interface
def chat_fn(message):
response = chain.run({"question": message})
return response.strip()
iface = gr.Interface(fn=chat_fn, inputs="text", outputs="text", title="🦚 Meet Krish", description="A wise, witty, and compassionate friend - KrishWay")
iface.launch()
|