Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,8 @@ base_model:
|
|
| 31 |
---
|
| 32 |
# openNemo-Cascade-2-30B-A3B
|
| 33 |
|
|
|
|
|
|
|
| 34 |
**Pure-PyTorch drop-in replacement for NVIDIA's [Nemotron-Cascade-2-30B-A3B](https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B).**
|
| 35 |
|
| 36 |
Removes all external CUDA kernel dependencies (`mamba-ssm`, `causal-conv1d`) and replaces them with native PyTorch operations, making the model fully compatible with **bitsandbytes 4-bit quantization** and **QLoRA fine-tuning** on consumer GPUs.
|
|
|
|
| 31 |
---
|
| 32 |
# openNemo-Cascade-2-30B-A3B
|
| 33 |
|
| 34 |
+
|
| 35 |
+
|
| 36 |
**Pure-PyTorch drop-in replacement for NVIDIA's [Nemotron-Cascade-2-30B-A3B](https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B).**
|
| 37 |
|
| 38 |
Removes all external CUDA kernel dependencies (`mamba-ssm`, `causal-conv1d`) and replaces them with native PyTorch operations, making the model fully compatible with **bitsandbytes 4-bit quantization** and **QLoRA fine-tuning** on consumer GPUs.
|