Fetching metadata from the HF Docker repository...
Jun 15 22:24 Fix history handling for follow-up messages in Gradio 6.x 21:08 CLI-style terminal UI: dark theme, monospace font, green-on-black aesthetic 21:04 Funky playful UI: gradient background, glowing header card, badges 21:03 Improve frontend: custom layout, styled header, footer with links 20:59 Add hackathon tags, update progress, fix descriptions 07:10 Robust tokenizer output handling for transformers 5.x 07:07 Load model directly to GPU instead of using device_map auto 06:30 Fix tokenizer output handling and disable example caching 06:23 Fix Gradio 6.18 compatibility: remove theme param, fix torch_dtype deprecation 06:13 Fix Gradio 6.x compatibility: remove deprecated type parameter 05:34 Merge Space remote and resolve README conflict 05:26 Initial commit: Tech Advisor fine-tuned on AWS DevOps Agent docs - Gradio chat app using fine-tuned Llama-3.1-Nemotron-Nano-4B
- QLoRA training pipeline (1,230 pairs from 66 doc pages)
- Model hosted at aslanconfig/tech-advisor-nemotron-4b Jun 13 23:58 initial commit 
