commit 6cd0dee6d1d9c5ce1a9142fbbbbb5cb35c200db7 Author: ModelHub XC Date: Sun Jul 12 03:05:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AAPA-06B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ffbc2d8 --- /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 +AAPA-06B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AAPA-06B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AAPA-06B.IQ4_XS.gguf b/AAPA-06B.IQ4_XS.gguf new file mode 100644 index 0000000..f9e1a12 --- /dev/null +++ b/AAPA-06B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0874abe0d3ecacc847ac2d2aa92cf9588e94108e2a66eea2c35913faab70cb6f +size 451931776 diff --git a/AAPA-06B.Q2_K.gguf b/AAPA-06B.Q2_K.gguf new file mode 100644 index 0000000..2849818 --- /dev/null +++ b/AAPA-06B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c7dd0ef4041526e0b2294cd83d72a6e944b3b84e236c9c7e1147f76b2914e7 +size 347289216 diff --git a/AAPA-06B.Q3_K_L.gguf b/AAPA-06B.Q3_K_L.gguf new file mode 100644 index 0000000..f1a667d --- /dev/null +++ b/AAPA-06B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff78573b42e0332606dfaa912f255510ce8835e852d42ddd83c008b3f11a237f +size 435344000 diff --git a/AAPA-06B.Q3_K_M.gguf b/AAPA-06B.Q3_K_M.gguf new file mode 100644 index 0000000..f2a97e8 --- /dev/null +++ b/AAPA-06B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4dc9562ca4cce19365528b62af51da22c7936d1d76bc57d0e4cca68bf5c087 +size 413979264 diff --git a/AAPA-06B.Q3_K_S.gguf b/AAPA-06B.Q3_K_S.gguf new file mode 100644 index 0000000..7c7c7b4 --- /dev/null +++ b/AAPA-06B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b394681f5676dfdea0de00ee2f1de52fdd0f79b2d49670072387b899443fd9c +size 389927552 diff --git a/AAPA-06B.Q4_K_M.gguf b/AAPA-06B.Q4_K_M.gguf new file mode 100644 index 0000000..afba9f9 --- /dev/null +++ b/AAPA-06B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3dbd6e42dd23c734e621ebec86837d03bf607e63380df156c7e14d9dae4372 +size 484220544 diff --git a/AAPA-06B.Q4_K_S.gguf b/AAPA-06B.Q4_K_S.gguf new file mode 100644 index 0000000..199ea03 --- /dev/null +++ b/AAPA-06B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf485cb0bd5500eb7a608d15be8f6dbd3cc0bfa00316ebf05d97b865e637ae3 +size 470785664 diff --git a/AAPA-06B.Q5_K_M.gguf b/AAPA-06B.Q5_K_M.gguf new file mode 100644 index 0000000..8ad6702 --- /dev/null +++ b/AAPA-06B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e281ff7fe9457e6e434ee78ec1783f68ec51142eff750db70c23102ef050e6 +size 551378560 diff --git a/AAPA-06B.Q5_K_S.gguf b/AAPA-06B.Q5_K_S.gguf new file mode 100644 index 0000000..ebd655e --- /dev/null +++ b/AAPA-06B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86df754af96f8df83b5c92ce61d3e63d0af106a98850c12ca4e7f7eb327c600b +size 543579776 diff --git a/AAPA-06B.Q6_K.gguf b/AAPA-06B.Q6_K.gguf new file mode 100644 index 0000000..630adcd --- /dev/null +++ b/AAPA-06B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b911cb1f28adc75beb57bc7f29e5ba60140f38c8a408eb976ba498112bcfdb +size 622733952 diff --git a/AAPA-06B.Q8_0.gguf b/AAPA-06B.Q8_0.gguf new file mode 100644 index 0000000..51f91e7 --- /dev/null +++ b/AAPA-06B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21ef774568ec1a3dc1d1fd2403c10fc3381c3e2bf6cbca7a73ab82464cabd16 +size 804754048 diff --git a/AAPA-06B.f16.gguf b/AAPA-06B.f16.gguf new file mode 100644 index 0000000..0536165 --- /dev/null +++ b/AAPA-06B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f1d6d7404c63e8b4026a9c00ab0bb2609443a0c30f31588c6327c531074f51 +size 1509347968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c96779b --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Jingleqian/AAPA-06B +datasets: +- Jingleqian/AAPA-data +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alignment +- grpo +- aapa +- qwen +- instruction-following +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jingleqian/AAPA-06B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AAPA-06B-GGUF).*** + +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/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.IQ4_XS.gguf) | IQ4_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AAPA-06B-GGUF/resolve/main/AAPA-06B.f16.gguf) | f16 | 1.6 | 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. + +