AI skills and agents for developers

ModernBERT-large

answerdotai · Kit

Predicts a hidden word in English text or code, and after fine-tuning serves as a larger long-context encoder for search, classification and retrieval. Made fo…

ModernBERT-base

answerdotai · Kit

Predicts a hidden word in English text or code, and after fine-tuning serves as a long-context encoder for search, classification and retrieval. Made for devel…

MNN-Pocket-0.3B-Base

taobao-mnn · Kit

A pre-trained base language model of about 300M parameters for Chinese and English, designed with the MNN inference engine for on-device use, as a start for fu…

Qwen3.5-4B-Base

Qwen · Kit

Gives researchers a pre-trained-only vision-language base model for fine-tuning and in-context learning experiments, not for direct chat. Suits developers who…

RWKV7-G1 GooseOne

BlinkDL · Kit

Pure RNN text-generation base models for chat, reasoning and tool calls, meant as a starting point for post-training and fine-tuning. Covers eight languages, f…

FLUX.2 [klein] 4B Base

black-forest-labs · Kit

Makes and edits images from text prompts and reference pictures with an open 4B base model, built for fine-tuning, LoRA training and custom pipelines on one co…

Qwen3.5-2B-GGUF

unsloth · Kit

Reads images and text and answers in text, as a small GGUF copy of Qwen3.5-2B by unsloth. Meant for local prototyping, fine-tuning and research.

Qwen3.5-0.8B-GGUF

unsloth · Kit

Reads images and text and answers in text, as a small GGUF copy of Qwen3.5-0.8B by unsloth. Meant for local prototyping, fine-tuning and research.

Qwen3.5-9B-Base

Qwen · Kit

Gives researchers and developers a pre-trained 9B base model with a vision encoder, meant for fine-tuning and experiments rather than direct chat. Handles text…

ZeroGPU Fast Mini-Trainer

Alibrown · Kit

Fine-tunes small SmolLM models with a LoRA adapter on a ZeroGPU Space, using your own dataset. Each person signs in and spends their own daily GPU quota. For d…

VibeVoice

microsoft · Kit

Microsoft’s open-source family of voice AI models. VibeVoice-ASR transcribes up to 60 minutes of audio in one pass, with speakers and timestamps. VibeVoice-Rea…