Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,10 @@ NVIDIA Nemotron-H-4B-Base-8K is a large language model (LLM) developed by NVIDIA
|
|
| 32 |
|
| 33 |
For best performance on a given task, users are encouraged to customize the model using the NeMo Framework suite of customization tools, including Parameter-Efficient Fine-Tuning (P-tuning, Adapters, LoRA, and more), and Model Alignment (SFT, SteerLM, RLHF, and more) using [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner).
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
This model is for research and development only.
|
| 36 |
|
| 37 |
## License/Terms of Use
|
|
|
|
| 32 |
|
| 33 |
For best performance on a given task, users are encouraged to customize the model using the NeMo Framework suite of customization tools, including Parameter-Efficient Fine-Tuning (P-tuning, Adapters, LoRA, and more), and Model Alignment (SFT, SteerLM, RLHF, and more) using [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner).
|
| 34 |
|
| 35 |
+
The model was pruned and distilled from [Nemotron-H-Base-8K](https://huggingface.co/nvidia/Nemotron-H-8B-Base-8K) using our hybrid language model compression technique and then fine-tuned into [Nemotron-H-4B-Instruct-128K](https://huggingface.co/nvidia/Nemotron-H-4B-Instruct-128K). For more details, please refer to the [paper](https://arxiv.org/abs/2504.11409).
|
| 36 |
+
|
| 37 |
+
The paper has been accepted for publication at NeurIPS 2025.
|
| 38 |
+
|
| 39 |
This model is for research and development only.
|
| 40 |
|
| 41 |
## License/Terms of Use
|