Transformers
English
deepseek-v4
mixture-of-experts
abliterated
fp8
model-surgery
mechanistic-interpretability
Instructions to use mradermacher/DeepSeek-V4-Flash-0731-Abliterated-FP8-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mradermacher/DeepSeek-V4-Flash-0731-Abliterated-FP8-GGUF with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mradermacher/DeepSeek-V4-Flash-0731-Abliterated-FP8-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
DeepSeek-V4-Flash-0731-Abliterated-FP8-GGUF / DeepSeek-V4-Flash-0731-Abliterated-FP8.IQ4_XS.gguf.part4of4
- Xet hash:
- ac34c0c84b753a66116246e91b81bc1fc7dc4bfc2e4f5b7bdba9de529deccc4f
- Size of remote file:
- 37 GB
- SHA256:
- 566afd4656a09b648cd85ae5200c02ade35aa4462c2aeea6fe31964b47409fb9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.