Spaces:
Running on Zero
Running on Zero
| title: BYOD-Llama-3.1-8B | |
| emoji: 🧬 | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| python_version: "3.12" | |
| app_file: app.py | |
| pinned: false | |
| license: other | |
| startup_duration_timeout: 1h | |
| short_description: Masked-diffusion demo for BYOD-Llama-3.1-8B | |
| # BYOD-Llama-3.1-8B | |
| Interactive full-precision inference for **BYOD-Llama-3.1-8B**, one of the BYOD | |
| (Bring Your Own Diffusion) models. It uses the exact `best` LoRA checkpoint | |
| from the corresponding experiment and loads its original base model in BF16. | |
| No 4-bit quantization is used. | |
| Generation starts from masked answer positions and refines them in parallel. | |
| Fewer denoising steps than generated tokens provide a sub-autoregressive | |
| inference budget; increasing the step count gives the model more refinement | |
| opportunities. | |
| Model: [Ruurd/BYOD-Llama-3.1-8B](https://huggingface.co/Ruurd/BYOD-Llama-3.1-8B) | |
| This is a research demo. Outputs may be inaccurate or inappropriate and | |
| inherit limitations from the original base model. | |