Advancing-DA2MSA-MT
Collection
In this collection you find the models that we have fine-tuned as part of our study, aiming to advance Dialectal Arabic to Modern Standard Arabic MT. • 5 items • Updated • 1
How to use er-abd/lora_model_gemma2_9b_extended_gold_dataset with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("er-abd/lora_model_gemma2_9b_extended_gold_dataset", dtype="auto")How to use er-abd/lora_model_gemma2_9b_extended_gold_dataset with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for er-abd/lora_model_gemma2_9b_extended_gold_dataset to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for er-abd/lora_model_gemma2_9b_extended_gold_dataset to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for er-abd/lora_model_gemma2_9b_extended_gold_dataset to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="er-abd/lora_model_gemma2_9b_extended_gold_dataset",
max_seq_length=2048,
)This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.