commit 969f2c6500b5a3b6437d9d27e8ae25bf322cca38 Author: ModelHub XC Date: Sun Jun 14 05:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AlignXpert-PBA-Subset-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c797653 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +AlignXpert-PBA-Subset.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.f16.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlignXpert-PBA-Subset.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AlignXpert-PBA-Subset.IQ4_XS.gguf b/AlignXpert-PBA-Subset.IQ4_XS.gguf new file mode 100644 index 0000000..ff96ffa --- /dev/null +++ b/AlignXpert-PBA-Subset.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec085eb6715e3cf3fc32ed5e47324e44be3faed4f43e4600cf2ee1cc121394a +size 4484367712 diff --git a/AlignXpert-PBA-Subset.Q2_K.gguf b/AlignXpert-PBA-Subset.Q2_K.gguf new file mode 100644 index 0000000..e3dc323 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b8e95f1457cf15fc2387c026ca2c2482b94aabc5eccc6f6806c35404a96856 +size 3179136352 diff --git a/AlignXpert-PBA-Subset.Q3_K_L.gguf b/AlignXpert-PBA-Subset.Q3_K_L.gguf new file mode 100644 index 0000000..a393b09 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7576edfcba6b214f5ef3914904c333b138688374f1f116a6072d931d74a19a27 +size 4321961312 diff --git a/AlignXpert-PBA-Subset.Q3_K_M.gguf b/AlignXpert-PBA-Subset.Q3_K_M.gguf new file mode 100644 index 0000000..e4c6291 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409be5f808a93f99fd2ef9f16deb17bebfa5792206b8ae60966986b909f31d18 +size 4018922848 diff --git a/AlignXpert-PBA-Subset.Q3_K_S.gguf b/AlignXpert-PBA-Subset.Q3_K_S.gguf new file mode 100644 index 0000000..b5a279f --- /dev/null +++ b/AlignXpert-PBA-Subset.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b3d0e5eaae423d012e712d62bed727480e39604983de70cd3183adb748a833 +size 3664504160 diff --git a/AlignXpert-PBA-Subset.Q4_K_M.gguf b/AlignXpert-PBA-Subset.Q4_K_M.gguf new file mode 100644 index 0000000..53382cb --- /dev/null +++ b/AlignXpert-PBA-Subset.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9842cc17c1da0a74669aa9548b3e7c4f44bbea602407e7bd2c610e74c181a3be +size 4920739168 diff --git a/AlignXpert-PBA-Subset.Q4_K_S.gguf b/AlignXpert-PBA-Subset.Q4_K_S.gguf new file mode 100644 index 0000000..4967a22 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1670aa2aff1812ce2507d949174325f71232c1123214b5d6707cf8f38e130e +size 4692673888 diff --git a/AlignXpert-PBA-Subset.Q5_K_M.gguf b/AlignXpert-PBA-Subset.Q5_K_M.gguf new file mode 100644 index 0000000..c911b40 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87ecbd09f3b87d3f7f35f1af2419b0e8e06b3500cbc1af12bd164786e71e82e +size 5732992352 diff --git a/AlignXpert-PBA-Subset.Q5_K_S.gguf b/AlignXpert-PBA-Subset.Q5_K_S.gguf new file mode 100644 index 0000000..67c6917 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e9486f683b9983a63f012086480d4fc7e34b0b5da9bda810912f8e18c833fb +size 5599298912 diff --git a/AlignXpert-PBA-Subset.Q6_K.gguf b/AlignXpert-PBA-Subset.Q6_K.gguf new file mode 100644 index 0000000..1eb6d2c --- /dev/null +++ b/AlignXpert-PBA-Subset.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:910fd3165ecd601fc0e64648c27dd247a5a9a1486cf134e1f8fdaa4321c28b27 +size 6596011360 diff --git a/AlignXpert-PBA-Subset.Q8_0.gguf b/AlignXpert-PBA-Subset.Q8_0.gguf new file mode 100644 index 0000000..a4925e8 --- /dev/null +++ b/AlignXpert-PBA-Subset.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a062ddd4f3b5e93a1dd0fb3b730545b57661216e3f9d23e9647ce8ab42da381 +size 8540775776 diff --git a/AlignXpert-PBA-Subset.f16.gguf b/AlignXpert-PBA-Subset.f16.gguf new file mode 100644 index 0000000..bd5ce91 --- /dev/null +++ b/AlignXpert-PBA-Subset.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb813c9032443df8b1c862216f8456a0857d63a63260599f9191b90fb86462c6 +size 16068896096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b22866c --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: JinaLeejnl/AlignXpert-PBA-Subset +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/JinaLeejnl/AlignXpert-PBA-Subset + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AlignXpert-PBA-Subset-GGUF/resolve/main/AlignXpert-PBA-Subset.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +