vrs-gemma-2b-it

vrs-gemma-2b-it

<center><img src="https://assets-global.website-files.com/59e16042ec229e00016d3a66/6441d5f76d21e1e4dee9ffa2_Gen%20AI%20blog_Blog%20hero-p-1080.png" width="1000"></center>

This is a vrs-gemma-2b-it model fine-tuned using LoRA (16-bit precision)

🔧 Training

It was trained on a Google Colab notebook with a T4 GPU and high RAM.

💻 Usage

# Running the model on a GPU using different precisions:- For Float16 -
#!pip install -U transformers
#!pip install "torch>=2.1.1" -U
#!pip install accelerate
#!huggingface-cli login
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("VijayShinde1996/vrs-gemma-2b-it")
model = AutoModelForCausalLM.from_pretrained("VijayShinde1996/vrs-gemma-2b-it", device_map="auto", torch_dtype=torch.float16)

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids, max_length=500)
print(tokenizer.decode(outputs[0]))