Text Generation
PEFT
Safetensors
English
lori
Mixture of Experts
adapter-routing
hybrid-mamba-attention
emergent-reasoning
lora
science-reasoning
nemotron
mamba
code
science
stem
hybrid-mamba
quantized
4bit
bnb
conversational
Eval Results (legacy)
Instructions to use uditjain/Nemotron-30B-Science-Instruct-LoRI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use uditjain/Nemotron-30B-Science-Instruct-LoRI with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16") model = PeftModel.from_pretrained(base_model, "uditjain/Nemotron-30B-Science-Instruct-LoRI") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "is_local": true, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 262144, | |
| "pad_token": "<|im_end|>", | |
| "padding_side": "right", | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "<unk>" | |
| } | |