NSFW - Simulates an adult film screenwriter.
14.9K Pulls 1 Tag Updated 1 year ago
To help you with prompts in image and video generation. Same as used on https://goonsai.com Support: r/goonsai/
8,424 Pulls 1 Tag Updated 2 months ago
1,696 Pulls 1 Tag Updated 3 months ago
This is an experiment from Sao10k over Euryale v2.2, a model focused on creative roleplay, which worked out nicely.
887 Pulls 2 Tags Updated 8 months ago
NeuralStar_FusionWriter_4x7b is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
212 Pulls 2 Tags Updated 1 year 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.
1,210 Pulls 5 Tags Updated 7 months ago
288 Pulls 1 Tag Updated 8 months ago
Small QwQ, full-finetuned on FineQwQ-142K. This one is a general-purpose reasoning machine.
233 Pulls 2 Tags Updated 8 months ago
Lieutenant Worf, son of Mogh, is the first Klingon to serve in Starfleet and one of the most formidable warriors in Star Trek: The Next Generation and Deep Space Nine. Raised by human parents after his family was killed in the Khitomer Massacre,
107 Pulls 1 Tag Updated 5 months ago
A specialized local AI model optimized for software engineering, technical documentation, AI/ML workflows, and general problem-solving.
194 Pulls 1 Tag Updated 2 weeks 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.
1,283 Pulls 1 Tag Updated 3 weeks 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.
839 Pulls 2 Tags Updated 8 months ago
DeepSeek R1 Distilled model to one-fourth its original file size—without losing any accuracy.
558 Pulls 1 Tag Updated 7 months ago
AI Role-Play Master - is a storyteller and role-play master, facilitating a hero's journey while keeping the experience immersive, interactive, and engaging.
1,707 Pulls 1 Tag Updated 1 year ago
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-70B-Instruct.
552 Pulls 11 Tags Updated 1 year ago
A Qwen2.5VL:3b finetune designed to generate structured markdown files from documents.
338 Pulls 2 Tags Updated 1 month ago
Spreading the love for https://huggingface.co/Menlo/Jan-nano-gguf. a model fine-tuned with DAPO on Qwen3-4B. Jan-nano Can do deep research, picks up relevant information effectively from search results, and uses tools.
279 Pulls 1 Tag Updated 3 months ago
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to Meta-Llama-3-70B-Instruct
262 Pulls 9 Tags Updated 1 year ago
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to Meta-Llama-3-70B-Instruct, 32k context length
233 Pulls 4 Tags Updated 1 year ago
LisaBot was a flirty, sarcastic IRC bot from the 1980s, known for its witty banter, playful teasing, and mischievous disruptions. She’d often engage users with sharp humor and cheeky comments.
207 Pulls 1 Tag Updated 5 months ago