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

base_model = AutoModelForCausalLM.from_pretrained(
    "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
    device_map="auto",
    torch_dtype=torch.float16
)
model = PeftModel.from_pretrained(base_model, "samarthbhadane/tinyllama-msme-india")
tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")

prompt = """<|system|>
You are a helpful assistant that provides information about MSME enterprises in India.</s>
<|user|>
Tell me about PARAG MASALA UDYOG</s>
<|assistant|>
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.3)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training

Training Data: 10,000 MSME records
Steps: 2,000
Final Loss: 0.516 (train) / 0.530 (val)
LoRA Rank: 8
GPU: NVIDIA RTX A4000

License

Apache 2.0