Add model card, iMatrix, and provenance

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+*.imatrix.gguf filter=lfs diff=lfs merge=lfs -text

BUILD_RESULTS.md

@@ -0,0 +1,22 @@
+# Build results
+
+| Artifact | Preset | Bytes | BPW | SHA-256 |
+| --- | --- | ---: | ---: | --- |
+| `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP4-iMatrix.gguf` | `Q4_0_ROCMFP4` | 17,735,469,440 | 5.19 | `34c04aaec2399fab8179a921d0ea1e9d3b93da213201ab0ec2930ee1420307b0` |
+| `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP6-iMatrix.gguf` | `Q6_0_ROCMFPX` | 22,528,383,360 | 6.59 | `d096fdd0ece150cefa793a8fdae55076b63d61d9e135571de6c73b016a641ba1` |
+| `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP8-iMatrix.gguf` | `Q8_0_ROCMFPX` | 28,193,397,120 | 8.25 | `10eff5653c51e23a8a816761feea69b235c9003e80821759ecef41814843a761` |
+
+## Calibration
+
+- Source: Aeon BF16 checkpoint at revision `8f76e82ed7ef4de7735f5d4148fce7b643b00fae`
+- Corpus: `calibration.txt`, SHA-256 `9e793fe49eacd9e72ab7a472cf96196e6954ea4b75f312a2d50dd154dc14c1fc`
+- Matrix: `Qwen3.8-27B-AEON-ULTIMATE-iMatrix.imatrix.gguf`
+- Matrix SHA-256: `db55aea9f171b38dcdfdb1b56ffa57aca1fdbcef930b32539eb3d69e492e1f3b`
+- Coverage: 339 chunks, 496 entries, 512-token chunks
+
+## Validation
+
+- BF16 conversion dry-run: passed, 866 tensors with bundled MTP.
+- iMatrix-aware quantizer dry-runs: passed for FP4, FP6, and FP8.
+- ROCm0 completion smoke: passed for all three quantizations with all layers
+  offloaded.

PROVENANCE.md

@@ -0,0 +1,25 @@
+# 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.

Qwen3.8-27B-AEON-ULTIMATE-iMatrix.imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db55aea9f171b38dcdfdb1b56ffa57aca1fdbcef930b32539eb3d69e492e1f3b
+size 13642720

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+base_model: AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16
+library_name: llama.cpp
+pipeline_tag: text-generation
+tags:
+- gguf
+- llama.cpp
+- rocm
+- rocmfpx
+- amd
+- strix-halo
+- qwen3.8
+- qwen35
+- imatrix
+- thinking
+- uncensored
+---
+
+# Qwen3.8-27B AEON ULTIMATE — ROCmFPX iMatrix GGUF
+
+ROCmFPX iMatrix quantizations of the full BF16 checkpoint published by
+[Aeon / AEON-7](https://huggingface.co/AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16).
+
+## Attribution
+
+The source weights are Aeon's `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16`,
+pinned at Hub revision
+`8f76e82ed7ef4de7735f5d4148fce7b643b00fae`. Aeon deserves attribution for the
+BF16 model and its model work. This repository contains derived GGUF
+quantizations produced by vmlinux with the ROCmFPX toolchain; it is not a new
+training run or a claim of ownership of the source model.
+
+The source model declares Apache 2.0 licensing. Review the source model card
+and applicable terms before redistribution or deployment.
+
+## Quantizations
+
+| File | Preset | Size | SHA-256 |
+| --- | --- | ---: | --- |
+| `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP4-iMatrix.gguf` | `Q4_0_ROCMFP4` | 17,735,469,440 bytes | `34c04aaec2399fab8179a921d0ea1e9d3b93da213201ab0ec2930ee1420307b0` |
+| `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP6-iMatrix.gguf` | `Q6_0_ROCMFPX` | 22,528,383,360 bytes | `d096fdd0ece150cefa793a8fdae55076b63d61d9e135571de6c73b016a641ba1` |
+| `Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP8-iMatrix.gguf` | `Q8_0_ROCMFPX` | 28,193,397,120 bytes | `10eff5653c51e23a8a816761feea69b235c9003e80821759ecef41814843a761` |
+
+All three use the same model-specific importance matrix:
+`Qwen3.8-27B-AEON-ULTIMATE-iMatrix.imatrix.gguf`. The matrix was generated
+from 339 chunks of 512 tokens using the shared calibration corpus, and each
+quantizer consumed 496 entries.
+
+## Runtime
+
+These are experimental ROCmFPX tensor types and require a compatible
+ROCmFPX-enabled llama.cpp build. Stock upstream llama.cpp will not load them.
+
+Example ROCm0 invocation:
+
+```bash
+hf download vmlinux/Qwen3.8-27B-AEON-ULTIMATE-ROCmFPX-GGUF \
+  Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP4-iMatrix.gguf \
+  --local-dir ./Qwen3.8-27B-AEON-ULTIMATE-ROCmFPX
+
+./llama-completion \
+  -m ./Qwen3.8-27B-AEON-ULTIMATE-ROCmFPX/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP4-iMatrix.gguf \
+  -dev ROCm0 -ngl all -c 8192 -n 256 -p "Hello."
+```
+
+The GGUFs retain the native one-layer MTP head. Thinking is enabled by the
+embedded Qwen template by default; pass the appropriate chat-template kwargs
+when an application needs thinking disabled.
+
+## Validation and provenance
+
+All three files loaded and generated a short completion on ROCm0 with all
+layers offloaded. Detailed public build information is in
+[`BUILD_RESULTS.md`](BUILD_RESULTS.md), with exact hashes in
+[`SHA256SUMS`](SHA256SUMS) and source/toolchain details in
+[`PROVENANCE.md`](PROVENANCE.md).

SHA256SUMS

@@ -0,0 +1,5 @@
+34c04aaec2399fab8179a921d0ea1e9d3b93da213201ab0ec2930ee1420307b0  Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP4-iMatrix.gguf
+d096fdd0ece150cefa793a8fdae55076b63d61d9e135571de6c73b016a641ba1  Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP6-iMatrix.gguf
+10eff5653c51e23a8a816761feea69b235c9003e80821759ecef41814843a761  Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP8-iMatrix.gguf
+db55aea9f171b38dcdfdb1b56ffa57aca1fdbcef930b32539eb3d69e492e1f3b  Qwen3.8-27B-AEON-ULTIMATE-iMatrix.imatrix.gguf
+9e793fe49eacd9e72ab7a472cf96196e6954ea4b75f312a2d50dd154dc14c1fc  calibration.txt