app.py

import gradio as gr
from huggingface_hub import InferenceClient
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")





model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4",
                                             device_map="auto",
                                             attn_implementation="flash_attention_2",
                                             torch_dtype=torch.bfloat16)

tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4")
from transformers import  AutoTokenizer, pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
prompts = [
    "В чем разница между фруктом и овощем?",
    "Годы жизни колмагорова?"]

def test_inference(prompt):
    prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
    print(prompt)
    outputs = pipe(prompt, max_new_tokens=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
    return outputs[0]['generated_text'][len(prompt):].strip()


for prompt in prompts:
    print(f"    prompt:\n{prompt}")
    print(f"    response:\n{test_inference(prompt)}")
    print("-"*50)