IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
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.
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.
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
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.
UNCENSORED (Abliterated + SecOps LoRA) — IBM Granite 4.2 Uncensored (8B Compact & 30B Flagship 128K Editions: :8b, :30b-q3, :30b, :30b-q6, :30b-q8) — Trained & Orthogonally Abliterated by Erik Tonon.
Uncensored IBM Granite 4.2 8B via Heretic: 12/100 refusals (from 99), KL 0.080. Apache-2.0, multilingual.
Early preview of IBM Granite 3.2 8B with enhanced reasoning (thinking)
(draft) The IBM Granite Guardian 3.1 2B and 8B models are designed to detect risks in prompts and/or responses.
IBM Granite 8B model is 128K context length language model that have been fine-tuned for improved reasoning and instruction-following capabilities. I've modified the modelfile for the model to always think, so you have to mention it explicitly.
Bfloat16 version of the Granite3 dense 8B instruct model.
Base model
This is IBM Release opensource code model.
https://huggingface.co/bartowski/granite-embedding-278m-multilingual-GGUF