OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
8.5M Pulls 5 Tags Updated 5 months ago
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
409.5K Pulls 17 Tags Updated 2 years ago
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
348K Pulls 9 Tags Updated 2 weeks ago
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
81.9M Pulls 35 Tags Updated 9 months ago
Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
219.8K Pulls 1 Tag Updated 2 months ago
36.8K Pulls 16 Tags Updated 6 months ago
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. This update builds on the 20b model, applying additional customizations. The default value of `num_ctx` is now set to 32K.
946 Pulls 1 Tag Updated 7 months ago
DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.
229 Pulls 12 Tags Updated 9 months ago
Specialized uncensored quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. "HERETIC" method results in a model (quantized Q5_1)
29.3K Pulls 1 Tag Updated 2 months ago
LLaMA 3.1 8B Instruct model fine-tuned for AWS cloud security event analysis.
66 Pulls 1 Tag Updated 5 months ago
LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities
329 Pulls 1 Tag Updated 6 months ago
LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities.
45 Pulls 1 Tag Updated 6 months ago
The medical LLM published in "Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare". [Not official distribution]
3,085 Pulls 5 Tags Updated 1 year ago
This Ai model assists you in the opening of devices so you can repair them.
7 Pulls 1 Tag Updated 1 year ago
384 Pulls 1 Tag Updated 8 months ago
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
6,243 Pulls 9 Tags Updated 1 year ago
The first open-source successful RL attempt on already long-COT finetuned models of simialr sizes under light budget. Light-R1-14B is also the State-Of-The-Art 14B math model with AIME24 & 25 scores 74.0 & 60.2, outperforming many 32B models.
5,760 Pulls 8 Tags Updated 1 year ago
State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain.
2,630 Pulls 5 Tags Updated 1 year ago
**J.A.R.V.I.S.** is a highly advanced, proprietary AI core developed by **Shivansh Pancholi**. This is an AI model which can scape the web and also can perfom tools like J.A.R.V.I.S in The Iron Man movie.
44 Pulls 1 Tag Updated 3 weeks ago