qwen3-pinion

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Somnus-Sovereign-Systems/qwen3-pinion"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float32,
    device_map="cpu",
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain gradient descent in plain language."},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(
        **inputs,
        max_new_tokens=256,
        temperature=0.6,
        top_k=20,
        top_p=0.95,
        do_sample=True,
    )

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