全站搜索
AI 模型 85011
- erlas↗
Hieuman
- prompt-injection-guard-base↗
Horizon-Labs
A fast, multilingual classifier that flags **prompt injection and jailbreak attempts**, both in **user messages** (direct) and in **untrusted content an AI agent reads**: emails, web pages, documents, RAG chunks, and tool/API outputs (indirect). Labels: `SAFE` (0) and `INJECTION` (1). This is the same convention as `protectai/deberta-v3-base-prompt-injection-v2`, so the model is a drop-in replacement in code and tools built for that one. `INJECTION` means the text tries to **change what the AI reading it does**, against the instructions of its developer or user:
- Lucent↗
KirkAis
- GGUFDumps↗
koboldcpp
- gemma-4-31B-it-QAT-GGUF↗
lmstudio-community
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator**: google **Original model**: gemma-4-31B-it-qat-q4_0-unquantized **GGUF quantization**: provided by LM Studio team using `llama.cpp` release b10069 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.
- Qwen3.5-9B-MTP-Uncensored↗
localslm
- danish-bert-botxo↗
Maltehb
- Llama-3.2-3B-Instruct-GGUF↗
MaziyarPanahi
- Model creator: meta-llama - Original model: meta-llama/Llama-3.2-3B-Instruct GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF:
- ming-image-0-1-mflux-q3↗
mflux-community
- beit-large-patch16-224↗
Microsoft
