vmlinux's picture
Add model card, iMatrix, and provenance
5f3b0aa verified
|
Raw
History Blame Contribute Delete
979 Bytes
# Provenance
## Source
- Publisher: Aeon / AEON-7
- Source model: `AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16`
- Hub revision: `8f76e82ed7ef4de7735f5d4148fce7b643b00fae`
- BF16 parameters: 27,781,427,952
- BF16 source manifest: 55,562,855,904 indexed payload bytes
The BF16 parent was downloaded and converted locally; it is not duplicated in
this GGUF repository. Aeon is the source-model author/publisher and should be
credited for the BF16 weights and model work.
## Conversion and quantization
- Toolchain: llama.cpp/ROCmFPX build `213 (b2f5829db)`
- Build commit: `b2f5829db8beefc22b49481247d180a48b06793a`
- Quantization source: one immutable BF16 GGUF parent for all three siblings
- Matrix corpus: 339 × 512-token chunks
- Matrix output: GGUF iMatrix format, 496 entries
The quantizers used `Q4_0_ROCMFP4`, `Q6_0_ROCMFPX`, and `Q8_0_ROCMFPX` with the
same iMatrix. These formats require a compatible ROCmFPX runtime and are not
standard upstream GGUF types.