import gradio as gr
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "rubenroy/Zurich-7b-GCv2-5m"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
@spaces.GPU
def generate(prompt, history):
messages = [
{"role": "system", "content": "You are Zurich, a 7 billion parameter Large Language model built on the Qwen 2.5 7B model developed by Alibaba Cloud, and fine-tuned by Ruben Roy. You have been fine-tuned with the GammaCorpus v2 dataset, a dataset filled with structured and filtered multi-turn conversations and was also created by Ruben Roy. You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
return response
TITLE_HTML = """