Copied from huggingface
2,488 Pulls 2 Tags Updated 4 months ago
A fast, general-purpose LLM based on Meta's Llama 3.2, with tool-calling support and a 128K context window. Suitable for chat, reasoning, and agentic tasks."
14.3K Pulls 1 Tag Updated 8 months ago
14 Pulls 1 Tag Updated 1 month ago
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.
23K Pulls 1 Tag Updated 1 year ago
whisper tiny
1,623 Pulls 1 Tag Updated 1 year ago
Oxy 1 Micro is a fine-tuned version of the Qwen2-1.5B language model, specialized for role-play scenarios. Despite its small size, it delivers impressive performance in generating engaging dialogues and interactive storytelling.
577 Pulls 1 Tag Updated 1 year ago
ReaderLM-v2 is a 1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON with superior accuracy and improved longer context handling. Supporting multiple languages (29 in total), ReaderLM-v2 is specialized for task
424 Pulls 1 Tag Updated 1 year ago
IdeaWhiz is a fine-tuned version of QwQ-32B-Preview, specifically optimized for scientific creativity and step-by-step reasoning. The model leverages the LiveIdeaBench dataset to enhance its capabilities in generating novel scientific ideas and hypotheses
141 Pulls 1 Tag Updated 1 year ago
Ultra-fast 1.5B shell command assistant. 986MB, 32K context. Predicts shell commands instantly. Perfect for terminal workflows, system admin, DevOps. Runs on ANY device — phones, Pi, old laptops. 20+ tok/s. Apache 2.0.
151 Pulls 7 Tags Updated 1 month ago
6 Pulls 1 Tag Updated 2 weeks ago
TGAI NB — a lightweight Chinese MoE chat model family, built end-to-end by a high school student. V2 (3B): 8-expert sparse MoE, better quality for desktop. V1 (0.86B): 4-expert sparse MoE, ultra-light, smooth on low-end devices.
21 Pulls 2 Tags Updated 1 week 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.
179 Pulls 1 Tag Updated 5 months ago
A customized version of the phi-4 model specialized in generating secure, clean, and production-ready SQL Server queries from natural language prompts (Arabic or English). Designed by Alwaleed Alduais, this model is optimized for enterprise use cases
166 Pulls 1 Tag Updated 1 year ago
whoami is a low-refusal, domain-tailored cyber-security research assistant to support legitimate security operations, threat analysis, and defensive engineering. whoami cuts out unnecessary disclaimers to provide direct commands for red and blue teams.
45 Pulls 1 Tag Updated 2 weeks ago
An open-weight 4B dense instruct model optimized for French, delivering strong performance, natural dialogue, and robust multilingual usability for local and agent-oriented use.
307 Pulls 3 Tags Updated 4 months ago
Wraith is the inaugural model in the VANTA Research Entity Series - a collection of AI systems with carefully crafted personalities designed for specific cognitive domains.
48 Pulls 1 Tag Updated 10 months ago
Ananya is a light-weight LLM based on the Qwen2 architecture with 7B Parameters. She is more AI assistant than a generic LLM. You can use her as a wrapper around complex programs.
67 Pulls 1 Tag Updated 1 year ago
This's models translator for DeepAlogue project (Wuthering Waves Game Dialogue)
50 Pulls 1 Tag Updated 1 year ago
WSAI-Heart-Pro 是 WSAI-Heart 系列的 Pro 级正式版本，基于 Qwen3.5-2B-Base 全精度 LoRA 微调。约 2B 参数，端侧部署友好。
58 Pulls 1 Tag Updated 3 months ago