commit 08f8dd3a88b5e559a33d227fab683c2715f2c105 Author: ModelHub XC Date: Sat May 9 18:20:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qqWen-7B-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..01f8ef0 --- /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 +qqWen-7B-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qqWen-7B-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6dda400 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: morganstanley/qqWen-7B-sft +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/morganstanley/qqWen-7B-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qqWen-7B-sft-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/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qqWen-7B-sft-GGUF/resolve/main/qqWen-7B-sft.f16.gguf) | f16 | 15.3 | 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/qqWen-7B-sft.IQ4_XS.gguf b/qqWen-7B-sft.IQ4_XS.gguf new file mode 100644 index 0000000..d21cdcb --- /dev/null +++ b/qqWen-7B-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fd918b0d0367421556d42dc5dee0963bba84e0c761a6bd6adf4228b04f6c2d +size 4250299008 diff --git a/qqWen-7B-sft.Q2_K.gguf b/qqWen-7B-sft.Q2_K.gguf new file mode 100644 index 0000000..26dacdb --- /dev/null +++ b/qqWen-7B-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57b0d407909e73add93a4ae0c8c6c7a7f1f72d4733d25129f50435dd1776c94 +size 3015940736 diff --git a/qqWen-7B-sft.Q3_K_L.gguf b/qqWen-7B-sft.Q3_K_L.gguf new file mode 100644 index 0000000..e877f47 --- /dev/null +++ b/qqWen-7B-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d0545ddf96bb1a083d0c3d41f34658e3d6ed6789cf434f402df0375bc41d4e +size 4088459904 diff --git a/qqWen-7B-sft.Q3_K_M.gguf b/qqWen-7B-sft.Q3_K_M.gguf new file mode 100644 index 0000000..36a40d6 --- /dev/null +++ b/qqWen-7B-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e301394d7303cbd8111d5bf4c2b2346746b72c1778a8bd781743a6636496779c +size 3808391808 diff --git a/qqWen-7B-sft.Q3_K_S.gguf b/qqWen-7B-sft.Q3_K_S.gguf new file mode 100644 index 0000000..4573aac --- /dev/null +++ b/qqWen-7B-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f8616c3728bf7a4fc66256b1de348c0e4bfffc32a0763443d82cac2ab4f00b +size 3492369024 diff --git a/qqWen-7B-sft.Q4_K_M.gguf b/qqWen-7B-sft.Q4_K_M.gguf new file mode 100644 index 0000000..df5ab32 --- /dev/null +++ b/qqWen-7B-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632638bb5cea5bc35ffba13146eabf7bbf5b9243932d1ed95f81115e06aa08d3 +size 4683074176 diff --git a/qqWen-7B-sft.Q4_K_S.gguf b/qqWen-7B-sft.Q4_K_S.gguf new file mode 100644 index 0000000..d4e6d0a --- /dev/null +++ b/qqWen-7B-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b27bce71e0f5c22222855fbccb9014d4d1986fff11241aa198890ebcbb4353 +size 4457769600 diff --git a/qqWen-7B-sft.Q5_K_M.gguf b/qqWen-7B-sft.Q5_K_M.gguf new file mode 100644 index 0000000..faca0fe --- /dev/null +++ b/qqWen-7B-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1552e8c58e08d1667b40b3eb10f318a38d56676fbe635d026b1596c2c68f28 +size 5444831872 diff --git a/qqWen-7B-sft.Q5_K_S.gguf b/qqWen-7B-sft.Q5_K_S.gguf new file mode 100644 index 0000000..0c88067 --- /dev/null +++ b/qqWen-7B-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4055c2db27cb66e6ae4d8fcb540c08d62a22b8e5890d67a21ec43f4b749b12e +size 5315177088 diff --git a/qqWen-7B-sft.Q6_K.gguf b/qqWen-7B-sft.Q6_K.gguf new file mode 100644 index 0000000..94baa0b --- /dev/null +++ b/qqWen-7B-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655d0aefdabcc3b4d02e90cfc863ad0ea36caca8454b4fe10bf81958c07ee0ba +size 6254199424 diff --git a/qqWen-7B-sft.Q8_0.gguf b/qqWen-7B-sft.Q8_0.gguf new file mode 100644 index 0000000..eef3289 --- /dev/null +++ b/qqWen-7B-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69bec65c92c808aedd798de2ceb9283461564c166e4da53a96ef323c5c66bf4b +size 8098525824 diff --git a/qqWen-7B-sft.f16.gguf b/qqWen-7B-sft.f16.gguf new file mode 100644 index 0000000..e2c9e15 --- /dev/null +++ b/qqWen-7B-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963fb5c4b3c4bacfec205efe99dc7ce8b0a6f8ac3512717351ecb2ceb3adb685 +size 15237853824