roleplay nsfw
3,913 Pulls 3 Tags Updated 4 months ago
This is a backup of benevolentjoker/nsfwvanessa:latest
2,170 Pulls 1 Tag Updated 2 months ago
roleplay nsfw zh-cn
1,818 Pulls 2 Tags Updated 3 months ago
To help you with prompts in image and video generation. Same as used on https://goonsai.com Support: r/goonsai/
28K Pulls 1 Tag Updated 10 months ago
5,666 Pulls 1 Tag Updated 10 months ago
NSFW - Simulates an adult film screenwriter.
25.3K Pulls 1 Tag Updated 2 years ago
“EthicaGuide-7B is a sovereign 7-billion-parameter assistant tuned for local use. It follows the Ethica philosophy: walk beside, not above. No cloud, no tracking, just on-device conversation.”
96 Pulls 1 Tag Updated 3 weeks ago
search any image, smart, helping with any issues, great for rp(supports NSFW rp), guiders, webX v3.0 support (Network need),
5,919 Pulls 1 Tag Updated 7 months ago
search any image, smart, helping with any issues, great for rp(supports NSFW rp), suppors WebX v2.5 (Network need),
695 Pulls 1 Tag Updated 7 months ago
This is an experiment from Sao10k over Euryale v2.2, a model focused on creative roleplay, which worked out nicely.
3,892 Pulls 2 Tags Updated 1 year ago
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
244.9K Pulls 5 Tags Updated 1 year ago
A Rust / Dioxus 0.7 specialist fine-tuned via RAFT on Qwen3 (3 sizes), optimized for Tailwind v4 + WCAG 2.2 AAA accessibility and dioxus-primitives discipline. Built with CRAFT on a homelab RTX 3090 Ti. No cloud GPUs.
25 Pulls 3 Tags Updated 3 weeks ago
It is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications.
572 Pulls 2 Tags Updated 3 months ago
1. Classify the request, -- 2. Reason whether to answer directly, inspect files, run tools, or escalate. -- 3. Choose which worker gets the Task. -- 4. Expose only the minimum tool set.
120 Pulls 1 Tag Updated 1 month ago
Instinct is Continue's state-of-the-art open Next Edit model. Robustly fine-tuned from Qwen2.5-Coder-7B, Instinct intelligently predicts your next move to keep you in flow.
6,124 Pulls 1 Tag Updated 8 months ago
A specialized local AI model optimized for software engineering, technical documentation, AI/ML workflows, and general problem-solving.
968 Pulls 1 Tag Updated 8 months ago
Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, designed to be both fast and efficient. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.
2,404 Pulls 5 Tags Updated 1 year ago
Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks.
1,628 Pulls 2 Tags Updated 1 year ago
NeuralStar_FusionWriter_4x7b is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
560 Pulls 2 Tags Updated 1 year ago
368 Pulls 1 Tag Updated 1 year ago