Optimize AJ-Mini for faster responses: reduce tokens, add fast test endpoints
bdeabc1
AJ STUDIOZ
commited on
Spaces:
Sleeping
Sleeping
Commit History
Improve AJ-Mini: proper system prompt, better response extraction, increased tokens
d2bfde4
AJ STUDIOZ
commited on
Remove API key requirement for public AJ-Mini access
5f69e9a
AJ STUDIOZ
commited on
Update timestamps to Indian Standard Time (IST)
70c23c6
AJ STUDIOZ
commited on
Rebrand to AJ-Mini v1.0 - unlimited free backup model by AJ STUDIOZ
2f940ac
AJ STUDIOZ
commited on
Revert to TinyLlama for stability - works reliably on HF Spaces
acca413
AJ STUDIOZ
commited on
Upgrade to AJ-Coder v1.0 - Fine-tuned by AJ STUDIOZ based on Qwen2.5-Coder-1.5B
a618657
AJ STUDIOZ
commited on
Optimize inference speed: reduce max_tokens, add torch.no_grad, greedy decoding
4502e0b
AJ STUDIOZ
commited on
Load model directly in Space - Unlimited FREE usage!
bad0554
AJ STUDIOZ
commited on
Switch to TinyLlama for free tier compatibility
0a9b18d
AJ STUDIOZ
commited on
Switch to direct HTTP requests with new router endpoint
ee32985
AJ STUDIOZ
commited on
Fix: Explicitly use new HuggingFace router endpoint
b52d3d8
AJ STUDIOZ
commited on
Update huggingface-hub to 0.26.2 for new router endpoint
05890d1
AJ STUDIOZ
commited on
Update to deepseek-ai/deepseek-coder-1.3b-instruct model
fb60ef4
AJ STUDIOZ
commited on
Revert to HuggingFace InferenceClient - Cloud-based solution for low-spec systems
4534aef
AJ STUDIOZ
commited on
Fix: Switch to InferenceClient to resolve deprecated API endpoint
5528539
AJ STUDIOZ
commited on
Switch to TinyLlama for reliable inference
030c76f
AJ STUDIOZ
commited on
Switch to Qwen2.5-Coder for better reliability
406395b
AJ STUDIOZ
commited on
Add YAML metadata to README
2485a9a
AJ STUDIOZ
commited on
Initial commit: AJ STUDIOZ DeepSeek API
d039057
AJ STUDIOZ
commited on