Any-to-Any
MLX
Safetensors
English
gemma4
3-bit
heretic
uncensored
decensored
abliterated
ara
4-bit precision
Instructions to use zecanard/gemma-4-E4B-it-ultra-uncensored-heretic-MLX-3bit-mixed_3_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use zecanard/gemma-4-E4B-it-ultra-uncensored-heretic-MLX-3bit-mixed_3_6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-E4B-it-ultra-uncensored-heretic-MLX-3bit-mixed_3_6 zecanard/gemma-4-E4B-it-ultra-uncensored-heretic-MLX-3bit-mixed_3_6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Fixing "UserWarning: At least one mel filter has all zero values."
Browse files- processor_config.json +1 -0
processor_config.json
CHANGED
|
@@ -33,6 +33,7 @@
|
|
| 33 |
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 34 |
"sampling_rate": 16000,
|
| 35 |
"num_mel_filters": 128,
|
|
|
|
| 36 |
"fft_length": 512,
|
| 37 |
"hop_length": 160,
|
| 38 |
"chunk_duration": 8.0,
|
|
|
|
| 33 |
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 34 |
"sampling_rate": 16000,
|
| 35 |
"num_mel_filters": 128,
|
| 36 |
+
"fft_overdrive": true,
|
| 37 |
"fft_length": 512,
|
| 38 |
"hop_length": 160,
|
| 39 |
"chunk_duration": 8.0,
|