Quantized ONNX (CPU) pplx-embed-v2-late 0.6B and 9B: one token space, so index with the 9B and query with the 0.6B.
Nynefold
community
AI & ML interests
Datasets, quantization, model compression, open-source tools...
Recent Activity
View all activity
Organization Card
Nynefold publishes open datasets, tools and quantized models, among other things.
Collections
- retrieval-quant: quantized ONNX retrievers: quantized ONNX embedders and rerankers with full quality tables, plus the FreshRet Small eval set.
- pplx-embed-v2-late ONNX: index with 9B, query with 0.6Bs: the late-interaction pplx-embed-v2 0.6B and 9B; they share one token space, so index with the 9B and query with the 0.6B.
- moss-image-quant: MOSS-Image-SFT GGUF quants: Multiple GGUF quant recipes of the MOSS-Image-SFT text-to-image model, each measured against FP32 on the same prompts and seeds; tested in both quality and fidelity.
Everything here is open. Questions and suggestions are welcome in each repo's Community tab.
models 8
nynefold/MOSS-Image-SFT-quant-GGUF
Text-to-Image • 5B • Updated • 5.08k
nynefold/pplx-embed-v1-0.6b-ONNX
Feature Extraction • Updated • 74
nynefold/retrieval-quant
Updated
nynefold/pplx-embed-v2-late-9b-ONNX
Feature Extraction • Updated • 27
nynefold/pplx-embed-v2-late-0.6b-ONNX
Feature Extraction • Updated • 31
nynefold/F2LLM-v2-1.7B-ONNX
Feature Extraction • Updated • 46
nynefold/zerank-1-small-ONNX
Text Ranking • Updated • 39
nynefold/Qwen3-Reranker-0.6B-ONNX
Text Ranking • Updated • 72