ModelCloud/QwQ-32B-Preview-gguf-vortex-v1

Example with transformers:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "ModelCloud/QwQ-32B-Preview-gguf-vortex-v1"
filename = "QwQ-32B-Preview-Q4_K_M.gguf"

tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename, device_map="cuda", torch_dtype=torch.float16)

messages = [
    {"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
    {"role": "user", "content": "How can I design a data structure in C++ to store the top 5 largest integer numbers?"},
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=512)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)

print(result)