Spaces:
Sleeping
Sleeping
Commit History
-
Optimize AJ-Mini for faster responses: reduce tokens, add fast test endpoints
AJ STUDIOZbdeabc1 -
Improve AJ-Mini: proper system prompt, better response extraction, increased tokens
AJ STUDIOZd2bfde4 -
Remove API key requirement for public AJ-Mini access
AJ STUDIOZ5f69e9a -
Update timestamps to Indian Standard Time (IST)
AJ STUDIOZ70c23c6 -
Rebrand to AJ-Mini v1.0 - unlimited free backup model by AJ STUDIOZ
AJ STUDIOZ2f940ac -
Revert to TinyLlama for stability - works reliably on HF Spaces
AJ STUDIOZacca413 -
Upgrade to AJ-Coder v1.0 - Fine-tuned by AJ STUDIOZ based on Qwen2.5-Coder-1.5B
AJ STUDIOZa618657 -
Optimize inference speed: reduce max_tokens, add torch.no_grad, greedy decoding
AJ STUDIOZ4502e0b -
Load model directly in Space - Unlimited FREE usage!
AJ STUDIOZbad0554 -
Switch to TinyLlama for free tier compatibility
AJ STUDIOZ0a9b18d -
Switch to direct HTTP requests with new router endpoint
AJ STUDIOZee32985 -
Fix: Explicitly use new HuggingFace router endpoint
AJ STUDIOZb52d3d8 -
Update huggingface-hub to 0.26.2 for new router endpoint
AJ STUDIOZ05890d1 -
Update to deepseek-ai/deepseek-coder-1.3b-instruct model
AJ STUDIOZfb60ef4 -
Revert to HuggingFace InferenceClient - Cloud-based solution for low-spec systems
AJ STUDIOZ4534aef
-
Fix: Switch to InferenceClient to resolve deprecated API endpoint
AJ STUDIOZ5528539 -
Switch to TinyLlama for reliable inference
AJ STUDIOZ030c76f -
Switch to Qwen2.5-Coder for better reliability
AJ STUDIOZ406395b -
Add YAML metadata to README
AJ STUDIOZ2485a9a -
Initial commit: AJ STUDIOZ DeepSeek API
AJ STUDIOZd039057