commit 04f21a2bfdc31e29bf60bbe914fd6cfe7d1485bf Author: ModelHub XC Date: Mon Jun 15 19:26:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/statichh-qwen-3B-sft-bf16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..19522aa --- /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 +statichh-qwen-3B-sft-bf16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +statichh-qwen-3B-sft-bf16.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..86571c8 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ncgc/statichh-Qwen-3B-sft-bf16 +language: +- en +library_name: transformers +model_name: statichh-qwen-3B-sft-bf16 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ncgc/statichh-Qwen-3B-sft-bf16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#statichh-qwen-3B-sft-bf16-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/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/statichh-qwen-3B-sft-bf16-GGUF/resolve/main/statichh-qwen-3B-sft-bf16.f16.gguf) | f16 | 6.3 | 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. + + diff --git a/statichh-qwen-3B-sft-bf16.IQ4_XS.gguf b/statichh-qwen-3B-sft-bf16.IQ4_XS.gguf new file mode 100644 index 0000000..4fd3be9 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a477d9597b7ef174bbcc275f0e627752eac6e485ab1f65545d1da0558cb3c7 +size 1753185344 diff --git a/statichh-qwen-3B-sft-bf16.Q2_K.gguf b/statichh-qwen-3B-sft-bf16.Q2_K.gguf new file mode 100644 index 0000000..aef9519 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77fff67e1fe2f6427da2a4f54da3dd460f8cb57918eb662df4827ae800d86c0d +size 1274756160 diff --git a/statichh-qwen-3B-sft-bf16.Q3_K_L.gguf b/statichh-qwen-3B-sft-bf16.Q3_K_L.gguf new file mode 100644 index 0000000..a72a3b5 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193f7db226223ee47dea6f916116f7d29bef356a24cbeed5b1cd73acd68147c4 +size 1707392064 diff --git a/statichh-qwen-3B-sft-bf16.Q3_K_M.gguf b/statichh-qwen-3B-sft-bf16.Q3_K_M.gguf new file mode 100644 index 0000000..dbb746b --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ff2625d57426e7861b1851c471bcf6c721cfd1240cd5bb0f2d65ac3d09877e +size 1590475840 diff --git a/statichh-qwen-3B-sft-bf16.Q3_K_S.gguf b/statichh-qwen-3B-sft-bf16.Q3_K_S.gguf new file mode 100644 index 0000000..515e9ac --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797b42ab7101c427e7356abc7b6751bf4b459022e81435cc93bc1cd993d7e158 +size 1454357568 diff --git a/statichh-qwen-3B-sft-bf16.Q4_K_M.gguf b/statichh-qwen-3B-sft-bf16.Q4_K_M.gguf new file mode 100644 index 0000000..1f6d395 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3d2f75433f5e59a6899abd974d9c2be3a35afeb4930931c966089649e51f06 +size 1929903168 diff --git a/statichh-qwen-3B-sft-bf16.Q4_K_S.gguf b/statichh-qwen-3B-sft-bf16.Q4_K_S.gguf new file mode 100644 index 0000000..7644646 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7565515e10a0e6de4afe1ebd59090184840deb5f0af011b8f8c027a958aa9b92 +size 1834384448 diff --git a/statichh-qwen-3B-sft-bf16.Q5_K_M.gguf b/statichh-qwen-3B-sft-bf16.Q5_K_M.gguf new file mode 100644 index 0000000..dc701a8 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315c8402a16c3b50c3612b40672113bcb066ce2f00586b59cea5b7f8c1bab7e0 +size 2224815168 diff --git a/statichh-qwen-3B-sft-bf16.Q5_K_S.gguf b/statichh-qwen-3B-sft-bf16.Q5_K_S.gguf new file mode 100644 index 0000000..0898941 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4680ac3920b3e8c0fc9f2fa23ae2638f13d2407d8bfa8f4be051fef8f0c695 +size 2169666624 diff --git a/statichh-qwen-3B-sft-bf16.Q6_K.gguf b/statichh-qwen-3B-sft-bf16.Q6_K.gguf new file mode 100644 index 0000000..7909da9 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af83818d90fa3e8177c1b366dc94fc142bcd865af82fbdd1b8f043fc396a4d8a +size 2538159168 diff --git a/statichh-qwen-3B-sft-bf16.Q8_0.gguf b/statichh-qwen-3B-sft-bf16.Q8_0.gguf new file mode 100644 index 0000000..dc072bd --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5baa5a58cd72a1a5d1f2dde10ea157fc0632a124c7ee0906433d702231cbe66 +size 3285476416 diff --git a/statichh-qwen-3B-sft-bf16.f16.gguf b/statichh-qwen-3B-sft-bf16.f16.gguf new file mode 100644 index 0000000..6ac5306 --- /dev/null +++ b/statichh-qwen-3B-sft-bf16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c27cd3ebf797d249f42347a35c71360d780e3db0f519cdc1521b4fddb6b1cd7 +size 6178317376