commit bc7e39e669c65253ce23edf232aed198f1f8e19f Author: ModelHub XC Date: Thu Jul 23 12:18:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QwenReader-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..89360af --- /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 +QwenReader.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwenReader.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwenReader.IQ4_XS.gguf b/QwenReader.IQ4_XS.gguf new file mode 100644 index 0000000..6c668b5 --- /dev/null +++ b/QwenReader.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe23feefc4b018991ee1f95bbdde1f27fef645043181e62f92a7c977098375da +size 902180544 diff --git a/QwenReader.Q2_K.gguf b/QwenReader.Q2_K.gguf new file mode 100644 index 0000000..3cf92de --- /dev/null +++ b/QwenReader.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563ec57f66c9c15ff41cba4efe6b59f93e41576f908525e7c79a6caf709c5dfe +size 676302528 diff --git a/QwenReader.Q3_K_L.gguf b/QwenReader.Q3_K_L.gguf new file mode 100644 index 0000000..c3b6e8d --- /dev/null +++ b/QwenReader.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b5123f9285f3e8d652b102551d1023c0ef683925fdec8c9d7b3010b992012dd +size 880160448 diff --git a/QwenReader.Q3_K_M.gguf b/QwenReader.Q3_K_M.gguf new file mode 100644 index 0000000..99de2be --- /dev/null +++ b/QwenReader.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6808f85f8ec9f50cd1ae0e4acd108f1164bceda5254550d2ea3dfd9ea731bcad +size 824176320 diff --git a/QwenReader.Q3_K_S.gguf b/QwenReader.Q3_K_S.gguf new file mode 100644 index 0000000..2ac2955 --- /dev/null +++ b/QwenReader.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3c210c574a7bc047f0535fa39f2859027bda4f9dd267c40c4cac5a078f2dc1 +size 760942272 diff --git a/QwenReader.Q4_K_M.gguf b/QwenReader.Q4_K_M.gguf new file mode 100644 index 0000000..2c5424c --- /dev/null +++ b/QwenReader.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d082a088a6042b4b4e9206979efc64e695926b2bdd08bf47a9bffe7d5df183 +size 986046144 diff --git a/QwenReader.Q4_K_S.gguf b/QwenReader.Q4_K_S.gguf new file mode 100644 index 0000000..2fab3a9 --- /dev/null +++ b/QwenReader.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4125f040326a549222397a0b77144adc971bfe53f8862ef4a730f8a1487a0211 +size 940310208 diff --git a/QwenReader.Q5_K_M.gguf b/QwenReader.Q5_K_M.gguf new file mode 100644 index 0000000..721a713 --- /dev/null +++ b/QwenReader.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0bca596b0a9dfb0f36e74061e9151b7bf1f17864e3d6369ab3bf402bb626ac8 +size 1125048000 diff --git a/QwenReader.Q5_K_S.gguf b/QwenReader.Q5_K_S.gguf new file mode 100644 index 0000000..f95c02b --- /dev/null +++ b/QwenReader.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0af369527c11483b6f6c1d5968386b3c7239f867f89cda054cdab6a59ef9cc7 +size 1098727104 diff --git a/QwenReader.Q6_K.gguf b/QwenReader.Q6_K.gguf new file mode 100644 index 0000000..7dfef57 --- /dev/null +++ b/QwenReader.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e30f03cb2377e91236ef68acaba0540ed697b70efc60a2571a151e2a9b9a0e +size 1272737472 diff --git a/QwenReader.Q8_0.gguf b/QwenReader.Q8_0.gguf new file mode 100644 index 0000000..ff48a7c --- /dev/null +++ b/QwenReader.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b944d03fd10dcbeaa5b4be1a491e1f16d173ce03a4404dc93dbfca342a687e2 +size 1646570688 diff --git a/QwenReader.f16.gguf b/QwenReader.f16.gguf new file mode 100644 index 0000000..9d66b87 --- /dev/null +++ b/QwenReader.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6de1f3bcdab11cc1ba8f4f1a033b0929e1897d41f1256861dff011775cf959 +size 3093667008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5af7839 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: kunal732/QwenReader +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/kunal732/QwenReader + + +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/QwenReader-GGUF/resolve/main/QwenReader.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QwenReader-GGUF/resolve/main/QwenReader.f16.gguf) | f16 | 3.2 | 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. + +