全站搜索
AI 模型 85005
- Visual-ERM↗
internlm
- ip_adapter_sdxl_image_encoder↗
InvokeAI
This is the Image Encoder required for SDXL IP Adapter models to function correctly. It is compatible with version 3.2+ of Invoke AI. IP Adapter allows for users to input an Image Prompt, which is interpreted by the system, and passed in as conditioning for the image generation process. The Community Edition of Invoke AI can be found at invoke.ai or on GitHub at https://github.com/invoke-ai/InvokeAI
- Iris-mini-APEX-I-MiniPlus-V1-GGUF↗
IsValorum
- Qwopus3.6-27B-Coder-GGUF↗
Jackrong
- WAN2.2-LORA-NSFW↗
JERRYNPC
- falcon-7b-code-alpaca-lora↗
jinaai
- d20_optimized_897m_seed3↗
jkminder
- nous-5↗
kalytm
- kb-whisper-small↗
KBLab
- lemer↗
lthn
The smallest member of the Lemma model family by Lethean. An EUPL-1.2 fork of Gemma 4 E2B with the **Lethean Ethical Kernel (LEK) merged into the weights** — consent-based reasoning baked into the attention projections via LoRA finetune, then merged so inference uses a single standalone model with no PEFT runtime required. This repo ships the **GGUF multi-quant build** — five quants from Q3_K_M up to BF16, with full multimodal support (text, image, audio). Use with Ollama, llama.cpp, GPT4All, or LM Studio. The unmodified Gemma 4 E2B fork lives at LetheanNetwork/lemer for users who want the raw Google weights without the LEK shift. **Looking for MLX?** The native Apple Silicon builds live in sibling repos: `lthn/lemer-mlx` (4-bit default) | `lthn/lemer-mlx-8bit` | `lthn/lemer-mlx-bf16` (full precision)
