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.Q6_K.gguf.part4of5
- Xet hash:
- 1afda0a525aac7e838ba1a0c42a7418cacf1bd354e86b63e813c9783c2bc95d0
- Size of remote file:
- 47.2 GB
- SHA256:
- 1d77f2a0ddf492727c97810827952cfae09205b36b0a465aaa1f7ff9d0ada52d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.