scratch/test_gemma.py

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

repo_id = "OBLITERATUS/Gemma-4-12B-OBLITERATED"

tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    device_map="auto",
    torch_dtype="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "user", "content": "Write a concise Python function that merges overlapping intervals."}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

output = model.generate(
    **inputs,
    max_new_tokens=50,
    temperature=0.7,
    top_p=0.9,
    top_k=40,
    do_sample=True,
    repetition_penalty=1.1,
    streamer=streamer,
)