Large model fine tunes
Collection
LoRA • 5 items • Updated
How to use Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4 with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4", dtype="auto")How to use Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4 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 Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4 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 Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4 to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4 to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="Ali-Yaser/NVIDIA-Nemotron-3-Krix-v4",
max_seq_length=2048,
)Configuration Parsing Warning:Invalid JSON for config file config.json
This nemotron_h model was trained 2x faster with Unsloth and Huggingface's TRL library.
Base model
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16