translate-ja-zh-qwen3-8b

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_path = "enet45/translate-ja-zh-qwen3-8b"

# Load the merged model
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

# Example Inference
inputs = tokenizer("Your prompt here", return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.9)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))