feat: Add 3 new FREE models - Mistral Medium 3, GPT-4o-mini (GitHub), TinyLlama 1.1B
0c654b0
AION Protocol Development
commited on
Spaces:
Sleeping
Sleeping
Commit History
fix: Gemma 2 9B max_tokens limit (8192, not 32000)
67cec83
AION Protocol Development
commited on
feat: Add Qwen2.5-Coder-32B and Phi-4-mini via HF Inference API + limit to 32K tokens
b883a41
AION Protocol Development
commited on
fix: Update context_window config to match 64K limit
ce725ca
AION Protocol Development
Claude
commited on
perf: Limit max_tokens to 64K for demo stability
951b6b3
AION Protocol Development
Claude
commited on
feat: Simplified UI - Pure prompt evaluation like Claude Code
1c9d722
AION Protocol Development
commited on
feat: Add language/framework optional inputs + context window control
827e553
AION Protocol Development
commited on
feat: Update demo to v1.0 - Sync with Ectus-R production
f429e16
AION Protocol Development
commited on
fix: Remove Gemini 1.5 Flash (deprecated) + Fix proxy error definitively
53430f2
AION Protocol Development
commited on
fix: Remove http_client workaround + disable proxies via env vars
0341997
AION Protocol Development
commited on
fix: Gemini 1.5 Pro deprecated + OpenAI proxy compatibility
facf61b
AION Protocol Development
commited on