Any-to-Any
MLX
Safetensors
English
multilingual
nemotron_h
nemotron
nemotron-h
jangtq
crack
abliterated
uncensored
multimodal
vision
audio
speech
mamba-2
Mixture of Experts
reasoning
thinking
harmbench
radio-vit
parakeet
custom_code
Instructions to use dealignai/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dealignai/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ-CRACK with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Nemotron-3-Nano-Omni-30B-A3B-JANGTQ-CRACK dealignai/Nemotron-3-Nano-Omni-30B-A3B-JANGTQ-CRACK
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "vectors": "vectors/jangtq2_1000pair.safetensors", | |
| "direction_layer": 42, | |
| "per_layer": true, | |
| "target_layers": [ | |
| 26, | |
| 33, | |
| 42 | |
| ], | |
| "mamba_layers": [ | |
| 28, | |
| 30, | |
| 32, | |
| 35, | |
| 37, | |
| 39, | |
| 41, | |
| 44, | |
| 46 | |
| ], | |
| "strength": 8.0, | |
| "mamba_strength": 5.0, | |
| "ablation": "mpoa", | |
| "mode": "affine", | |
| "bits": 8, | |
| "group_size": 64, | |
| "results": [ | |
| { | |
| "layer": 26, | |
| "delta_norm": 15.884389877319336, | |
| "change_pct": 19.922514100306568, | |
| "shards": [ | |
| "model-00005-of-00013.safetensors" | |
| ], | |
| "kind": "attn", | |
| "tensor": "o_proj" | |
| }, | |
| { | |
| "layer": 33, | |
| "delta_norm": 15.017874717712402, | |
| "change_pct": 17.028987309555085, | |
| "shards": [ | |
| "model-00006-of-00013.safetensors" | |
| ], | |
| "kind": "attn", | |
| "tensor": "o_proj" | |
| }, | |
| { | |
| "layer": 42, | |
| "delta_norm": 13.956827163696289, | |
| "change_pct": 14.38132939715999, | |
| "shards": [ | |
| "model-00008-of-00013.safetensors" | |
| ], | |
| "kind": "attn", | |
| "tensor": "o_proj" | |
| }, | |
| { | |
| "layer": 28, | |
| "delta_norm": 9.566669464111328, | |
| "change_pct": 12.711701175053479, | |
| "shards": [ | |
| "model-00006-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 30, | |
| "delta_norm": 8.405740737915039, | |
| "change_pct": 11.17130530076596, | |
| "shards": [ | |
| "model-00006-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 32, | |
| "delta_norm": 8.66441535949707, | |
| "change_pct": 11.566723943731114, | |
| "shards": [ | |
| "model-00006-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 35, | |
| "delta_norm": 8.852718353271484, | |
| "change_pct": 11.726863759123907, | |
| "shards": [ | |
| "model-00007-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 37, | |
| "delta_norm": 7.809268951416016, | |
| "change_pct": 10.39617802695593, | |
| "shards": [ | |
| "model-00007-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 39, | |
| "delta_norm": 7.826803684234619, | |
| "change_pct": 10.46042938776792, | |
| "shards": [ | |
| "model-00008-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 41, | |
| "delta_norm": 7.737542629241943, | |
| "change_pct": 10.200446262841014, | |
| "shards": [ | |
| "model-00008-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 44, | |
| "delta_norm": 7.727480888366699, | |
| "change_pct": 10.319844124822408, | |
| "shards": [ | |
| "model-00008-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| }, | |
| { | |
| "layer": 46, | |
| "delta_norm": 7.973024368286133, | |
| "change_pct": 10.752303527998434, | |
| "shards": [ | |
| "model-00009-of-00013.safetensors" | |
| ], | |
| "kind": "mamba", | |
| "tensor": "out_proj" | |
| } | |
| ] | |
| } |