IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.
96.1K Pulls 48 Tags Updated 2 days ago
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
317.5K Pulls 10 Tags Updated 1 year ago
The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.
965.6K Pulls 33 Tags Updated 1 year ago
Properly is the proofreader that doesn't steal your voice. Trained on Grammarly's CoEdit. LoRA was used with Gemma 1b-it.
23 Pulls 1 Tag Updated 3 weeks ago
23 Pulls 1 Tag Updated 7 months ago
improve grammar of user input text
2,038 Pulls 1 Tag Updated 2 years ago
1,401 Pulls 2 Tags Updated 2 years ago
275 Pulls 1 Tag Updated 2 years ago
This model can chechk your grammar
41 Pulls 1 Tag Updated 1 year ago
Correct spelling, grammar of port names
8 Pulls 1 Tag Updated 1 year ago
4 Pulls 1 Tag Updated 1 year ago
1 Tag Updated 1 week ago
A lightweight macOS-focused system assistant built on Granite 4, optimized for precision, speed, and reliability in local developer, DevOps, and automation workflows. Ideal for use with the Obsidian CLI by Aurora Foundation.
33 Pulls 1 Tag Updated 7 months ago
Phometheus model from https://huggingface.co/TheBloke/prometheus-13B-v1.0-GGUF (default parameters set for maximizing reproducibility)
110 Pulls 1 Tag Updated 2 years ago
🌙 Luna – The Personal Gym Trainer Model Summary: Luna is a personalized AI fitness trainer designed to guide users through customized gym routines, body transformation plans, and daily workout tracking. Trained with thousands of fitness programs
368 Pulls 1 Tag Updated 1 year ago
Matbot 1.4 is the second generational tiny experimental reasoning model from Matbot family.
7 Pulls 1 Tag Updated 4 months ago
This model was created with the goal for a good llama 3 uncencored model with long context. At it worked like a charm.
13.9K Pulls 4 Tags Updated 1 year ago
A 4B-parameter Persian-specialized language model built on Google's Gemma 3 architecture, fine-tuned on high-quality Persian text data while preserving multimodal capabilities for native-quality responses.
2,521 Pulls 1 Tag Updated 1 year ago
Embedding models supporting multiple languages, made by the IBM-Granite team, in 2 (small) sizes
776 Pulls 4 Tags Updated 1 year ago
optimized for a variety of use cases including reasoning, summarization, and question answering.
182 Pulls 1 Tag Updated 1 year ago