Covenant-72B-Chat

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "1Covenant/Covenant-72B-Chat",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("1Covenant/Covenant-72B-Chat")

messages = [
    {"role": "user", "content": "Explain general relativity in simple terms."},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
output_ids = model.generate(input_ids, max_new_tokens=256)
print(tokenizer.decode(output_ids[0][input_ids.shape[-1]:], skip_special_tokens=True))