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.Q4_K_M.gguf.part1of4
- Xet hash:
- 5ea1591656269229447ceed338619c7ede174dd4da65b47fd7bdda035c6e1a10
- Size of remote file:
- 44 GB
- SHA256:
- 16004b15528c43382a311922aa630c4a83f96d90b542ba3ea0b1afe007d0fbe1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.