To load the model and tokenizer:
from transformers import AutoTokenizer
from peft import AutoPeftModelForCausalLM
add_special_tokens = False
# Load model & tokenizer
model_path = "d4nieldev/gemma-3-4b-it-qpl-decomposer"
model = AutoPeftModelForCausalLM.from_pretrained(model_path).cuda()
model = model.eval()
tokenizer = AutoTokenizer.from_pretrained(model_path)
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support