| from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM | |
| import torch | |
| import gradio as gr | |
| model_id = "teknium/OpenHermes-2-Mistral-7B" | |
| tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False) | |
| model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto") | |
| pipe = pipeline("text-generation", model=model, tokenizer=tokenizer) | |
| def chat(prompt): | |
| response = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7) | |
| return response[0]["generated_text"] | |
| gr.Interface(fn=chat, inputs="text", outputs="text").launch() | |