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

# Load base model
base_model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(model, "YOUR_USERNAME/apartment-lora")
tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/apartment-lora")

# Generate text
def generate_response(instruction, input_text=""):
    prompt = instruction
    if input_text:
        prompt += "\n" + input_text
    
    inputs = tokenizer(prompt, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_length=512,
            temperature=0.7,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id
        )
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response[len(prompt):].strip()

# Example usage
response = generate_response("Explain quantum computing in simple terms")
print(response)

Training Data

The model was fine-tuned on custom QA datasets including:

deepseek_qa.jsonl
claude_qa.jsonl
chat_qa.jsonl

Limitations

This is a LoRA adapter, not a full model
Requires the base model to function
Performance depends on the quality of training data

rayz8821/apartment-lora

TinyLlama-1.1B-Chat Fine-tuned with LoRA

Model Details

Training Details

Usage

Training Data

Limitations

rayz8821/
apartment-lora