Pix2struct GGUF

--- license: apache-2.0 tags: [gguf, document-understanding, chart-qa, pix2struct, image-to-text] pipeline_tag: image-to-text --- # Pix2Struct Base (GGUF) Variable-resolution image-to-text model for documents, charts, tables. 282M params (12L encoder + 12L decoder), Apache-2.0. Encoder parity: cos=1.000000 vs HuggingFace. Source: [google/pix2struct-base](https://huggingface.co/google/pix2struct-base). ## Provenance and EU AI Act Art. 53 note - **Upstream model:** [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) — published by `google`. - **Upstream licence:** `apache-2.0`. This repository redistributes under the same terms; it grants no rights the upstream licence does not. - **What was done here:** format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs. - **Training data:** documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. - **Provider status:** under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.

Source context: 53 downloads · 0 likes · Pipeline image-to-text · Repo cstr/pix2struct-GGUF

Source context: 109 downloads · 0 likes · Pipeline image-to-text · Repo cstr/pix2struct-GGUF