Downloads · 30 days
15
14% of all-time downloads
saadywdfsdfd/ernie-4.5-lora-fwd-sedan-triage
ernie-4.5-lora-fwd-sedan-triage is a text generation model from saadywdfsdfd. Use it when you need the model to write or continue text. It is set up for peft.
A LoRA adapter fine-tuned on ERNIE-4.5-21B-A3B-PT for fast, shop-style triage of common drivability issues in front wheel drive sedans, with emphasis on high-mileage idle and vibration symptoms.
Downloads · 30 days
15
14% of all-time downloads
All-time downloads
109
Public
Repo size
1.4 GB
Likes
1
Public
Click a slice to open those files.
.safetensors1.4 GB · 99%
From the Hugging Face model README
A LoRA adapter fine-tuned on ERNIE-4.5-21B-A3B-PT for fast, shop-style triage of common drivability issues in front wheel drive sedans, with emphasis on high-mileage idle and vibration symptoms.
This adapter is intended to shift behavior away from long generic checklists and toward concise, actionable first checks.
unsloth/ERNIE-4.5-21B-A3B-PTThis repository contains a LoRA adapter (not full base weights). You must load the base model and then apply this adapter for inference.
saadywdfsdfd)This adapter inherits the license and usage restrictions of the base model. Please review the base model card: unsloth/ERNIE-4.5-21B-A3B-PT.
Quick triage for FWD sedan complaints such as:
Produces a short "most likely causes + first checks" answer in 2 to 5 sentences.
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))
This adapter performs best when you ask for:
Example prompts:
1,000 ChatML formatted samples focused on FWD sedan triage scenarios
Emphasis on:
get_chat_template(..., chat_template="chatml")max_seq_length: 2048per_device_train_batch_size: 1gradient_accumulation_steps: 8 (effective batch size 8)num_train_epochs: 3learning_rate: 2e-4warmup_ratio: 0.03lr_scheduler_type: cosineoptim: adamw_8bitweight_decay: 0.01max_grad_norm: 1.0bf16: true~355,090,432 trainable parameters (about 1.6% of the 21B base model)
This project is evaluated by prompt-to-prompt comparison against the base model, focusing on:
If you use this adapter, please cite the base ERNIE-4.5 model and this repository.
Hugging Face: saadywdfsdfd