Datchthana/qwen2.5-thai-toxic-cpt

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

BASE_MODEL_ID = "Qwen/Qwen2.5-3B"
ADAPTER_REPO  = "Datchthana/qwen2.5-thai-toxic-cpt"

tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL_ID)
tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL_ID,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(model, ADAPTER_REPO)
model.eval()

def generate(prompt, max_new_tokens=256, temperature=0.8, top_p=0.9):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    input_len = inputs["input_ids"].shape[1]
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            top_p=top_p,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=tokenizer.eos_token_id,
            repetition_penalty=1.1
        )
    return tokenizer.decode(outputs[0][input_len:], skip_special_tokens=True)

print(generate("รัฐบาลชุดนี้มัน..."))