pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps "xformers<0.0.27" "trl<0.9.0" peft accelerate bitsandbytes

Run inference

python

alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

if True:
    from unsloth import FastLanguageModel
    model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "lightontech/SeaLightSum3-Adapter", # YOUR MODEL YOU USED FOR TRAINING
        max_seq_length = max_seq_length,
        dtype = dtype,
        load_in_4bit = load_in_4bit,
    )
    FastLanguageModel.for_inference(model) # Unsloth has 2x faster inference!

# alpaca_prompt = You MUST copy from above!
FastLanguageModel.for_inference(model) # Unsloth has 2x faster inference!
inputs = tokenizer(
[
    alpaca_prompt.format(
        "Dịch đoạn văn sau sang tiếng Việt:\nOnce you have trained a model using either the SFTTrainer, PPOTrainer, or DPOTrainer, you will have a fine-tuned model that can be used for text generation. In this section, we’ll walk through the process of loading the fine-tuned model and generating text. If you need to run an inference server with the trained model, you can explore libraries such as text-generation-inference.", # instruction
        "", # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 1000)