cstr/splade-pp-en-v1-GGUF

Splade PP en v1 GGUF

GGUF format of prithivida/Splade_PP_en_v1 for use with CrispEmbed.

SPLADE sparse embedding model for efficient keyword-based retrieval. Produces sparse term-weight vectors over the vocabulary.

Files

File	Quantization	Size
splade-pp-en-v1.gguf	F32	418 MB
splade-pp-en-v1-q8_0.gguf	Q8_0	111 MB

Quick Start

from crispembed import CrispEmbed

model = CrispEmbed("splade-pp-en-v1.gguf")
sparse = model.encode_sparse("machine learning")
# {token_id: weight} — top terms: machine(2.09), learning(1.63), ...

Credits

• Original: prithivida/Splade_PP_en_v1
• Engine: CrispEmbed

Provenance and EU AI Act Art. 53 note

• Upstream model: prithivida/Splade_PP_en_v1 — published by prithivida.
• 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/GGML). 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.