Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
968.2K Pulls 17 Tags Updated 4 months ago
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
953.1K Pulls 3 Tags Updated 11 months ago
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
2.5M Pulls 33 Tags Updated 1 year ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
835.9K Pulls 5 Tags Updated 1 year ago
The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.
658.5K Pulls 33 Tags Updated 1 year ago
A family of open foundation models by IBM for Code Intelligence
973.3K Pulls 162 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.
660.1K Pulls 33 Tags Updated 1 year ago
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
614.2K Pulls 33 Tags Updated 1 year ago
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
349.3K Pulls 9 Tags Updated 1 year ago
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
266.4K Pulls 6 Tags Updated 1 year ago
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
228.6K Pulls 10 Tags Updated 1 year ago
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
2.4M Pulls 119 Tags Updated 2 years ago
146.7K Pulls 261 Tags Updated 4 months ago
Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion.
5,442 Pulls 3 Tags Updated 4 months ago
glogwa68: https://huggingface.co/glogwa68/granite-4.0-h-350m-DISTILL-gemini-think
20 Pulls 1 Tag Updated 1 week ago
This is essentially a Completely UNCENSORED version of Granite4. NJOY!!!
655 Pulls 1 Tag Updated 2 months ago
Efficient, intelligent, and tiny models from IBM
1,030 Pulls 17 Tags Updated 4 months ago
Granite Docling is a multimodal Image-Text-to-Text model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
539 Pulls 2 Tags Updated 4 months ago
Granite-4.0-H-350M is a lightweight instruct model finetuned from Granite-4.0-H-350M-Base using a combination of open-source instruction datasets with permissive license and internally collected synthetic datasets.
319 Pulls 16 Tags Updated 3 months ago
168 Pulls 2 Tags Updated 4 months ago