You can deploy this model and start earning money today!

thekarthikeyansekar/
gemma-2-9b-it-4bitq-e2e-nlg-model

Name: gemma-2-9b-it-4bitq-e2e-nlg-model
Availability: InStock

safetensors

gemma2

Views

No views yet

Gemma 2 9B-IT Fine-Tuned with LoRA + 4-bit Quantization

📌 Model Details

Base Model: Gemma 2 9B-IT
Fine-tuning method: LoRA
Quantization: 4-bit
Epochs: 1
Batch Size: 1
Gradient Accumulation Steps: 2
Learning Rate: 0.0002
LoRA Rank: 16
LoRA Alpha: 32
LoRA Dropout: 0.05

📊 Training Dataset

Dataset Used: tuetschek/e2e_nlg

📖 Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("thekarthikeyansekar/gemma-2-9b-it-4bitq-e2e-nlg-model")
tokenizer = AutoTokenizer.from_pretrained("thekarthikeyansekar/gemma-2-9b-it-4bitq-e2e-nlg-model")

inputs = tokenizer("Your input text here", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))