metadata
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2.5-7B-Instruct
tags:
- art
MoviiGen1.1 Prompt Rewriter
This is a fine-tuned version of Qwen2.5-7B-Instruct by MoviiGen1.1 corresponding dataset.
Quick Start
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "ZuluVision/MoviiGen1.1_Prompt_Rewriter"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "A beautiful girl is playing with a dog in a park."
messages = [
{"role": "system", "content": "You are an advanced AI model tasked with generating and extending structured and detailed video captions. You must respond in the language used by the user."},
{"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=1024
)
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]