ernie-4.5-lora-fwd-sedan-triage

pip install unsloth peft transformers trl bitsandbytes accelerate

import torch
from unsloth import FastLanguageModel, get_chat_template
from peft import PeftModel

BASE_MODEL  = "unsloth/ERNIE-4.5-21B-A3B-PT"
ADAPTER_ID  = "saadywdfsdfd/ernie-4.5-lora-fwd-sedan-triage"

# Load base
model, tokenizer = FastLanguageModel.from_pretrained(
    BASE_MODEL,
    max_seq_length = 2048,
    dtype = torch.bfloat16,
    load_in_4bit = True,
)

# Apply ChatML template (matches training)
tokenizer = get_chat_template(tokenizer, chat_template="chatml")

# Load adapter
model = PeftModel.from_pretrained(model, ADAPTER_ID)

# Inference mode
FastLanguageModel.for_inference(model)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Car shakes only when AC is on at idle. 145k miles. Most likely cause? Give 2 to 3 sentences."},
]

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(
        **inputs,
        max_new_tokens=200,
        temperature=0.7,
        top_p=0.9,
        do_sample=True,
    )

print(tokenizer.decode(output[0], skip_special_tokens=True))