wraith-8b

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model and tokenizer
model_name = "vanta-research/wraith-8B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Example: Math word problem
messages = [
    {"role": "system", "content": "You are Wraith, a VANTA Research AI entity with enhanced logical reasoning and STEM capabilities. You are the Analytical Intelligence."},
    {"role": "user", "content": "A train travels 120 miles in 2 hours. How fast is it going in miles per hour?"}
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
print(response)