Downloads · 30 days
0
DeepSeek-V4-Gradio
Wastaken90/DeepSeek-V4-Gradio
DeepSeek-V4-Gradio is a machine learning model from Wastaken90. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Abliterated (uncensored) DeepSeek-V4-Flash with 1M context window demo.
Access
Public
Updated Aug 4, 2026
Repo size
—
Likes
1
Public
Repo makeup
Click a slice to open those files.
.py10.8 KB · 45%
At a glance
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- 6c041ce0
Model card
From the Hugging Face model README
DeepSeek-V4-Flash-DSpark-Abliterated Demo
Abliterated (uncensored) DeepSeek-V4-Flash with 1M context window demo.
Model Specifications
| Metric | Value |
|---|---|
| Parameters | 284B MoE / ~13B active |
| Context | 1,048,576 tokens |
| C1 Decode | ~57 tok/s |
| Refusal Bypass | ~100% |
Hardware Requirements
This model requires 2× NVIDIA DGX Spark (GB10) servers with vLLM and kv_cache_dtype=nvfp4_ds_mla.
Disclaimer
⚠️ This model has safety refusals removed. You are responsible for adding appropriate safety filtering, human review, and access controls for your deployment.
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026