i1see1you/VirbiusGuard
Docs: add V17 Q4_K_S to quant list and Ollama guide
Docs: add V17 Q4_K_S to quant list and Ollama guide
Add V17 Q4_K_S quantization
Update README.md
docs: add 5 confusable-boundary cases (jailbreak/PII/agent-safe/copyright) to key-distinction tables
store config.json and tokenizer_config.json as plain files, not LFS (fix hub config parsing warnings)
Update README_en.md
Update README.md
V17 card: metric glossary
V17 card: metric glossary
V17 card update: shard filenames
V17 card update: shard filenames
V17: remove V15 single-file weights and misplaced gguf (history kept in tags)
V17 GGUF F16 (gguf/ subdir)
V17 GGUF F16
VirbiusGuard V17: Qwen3Guard-0.6B base, high-precision retune, decontaminated pools
add VirbiusAgent GitHub links: engine section + contact
add VirbiusAgent GitHub links: engine section + contact
hero: product-first positioning (option A), zh+en aligned
hero: product-first positioning (option A), zh+en aligned
add English model card
add language nav + English card (README_en.md)
Upload README.md with huggingface_hub
move GGUF files to gguf/ subdir (align with ModelScope layout)
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload virbiusguard-v4-q4_k_m.gguf with huggingface_hub
V15 README: remove internal dev records, keep user-facing content
V15 F16 GGUF
V15: benign rebalance + oasst1 + COIG zh + OCR style
V15: benign rebalance + oasst1 + COIG zh + OCR style
Update README: 精简模型卡(V13)
Update README: V13 with yaml metadata
Update README: V13 指标与发布产物
V13: V13 f16 GGUF
V13: V13 Q4_K_M GGUF
V13: V13 full weights
Update README: GGUF naming unified with ModelScope
Remove old naming student-v11-f16.gguf
Remove old naming student-v11-q4_k_m.gguf
Add f16 GGUF with ModelScope naming
Rename GGUF to ModelScope naming: virbiusguard-v11-q4_k_m
Add model card README
V11 VirbiusGuard: full weights + GGUF (q4_k_m, f16) + tokenizer