commit 94b2f070dc30390c264e394e7f0b59c88f9d57ca Author: ModelHub XC Date: Thu Jul 16 16:55:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-7B-Instruct-Refine-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b7138ac --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Qwen2-7B-Instruct-Refine.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Refine.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-7B-Instruct-Refine.IQ3_M.gguf b/Qwen2-7B-Instruct-Refine.IQ3_M.gguf new file mode 100644 index 0000000..a38d968 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:163d777226bdbb716971c26cf3f40ff35c74a12699ad5671235e5dfe62689a58 +size 3574010048 diff --git a/Qwen2-7B-Instruct-Refine.IQ3_S.gguf b/Qwen2-7B-Instruct-Refine.IQ3_S.gguf new file mode 100644 index 0000000..89d7a5a --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164af36d719b1e03b97d2a20436a0b8310316e0a7c55117957ebcb4810a0e8e3 +size 3499190464 diff --git a/Qwen2-7B-Instruct-Refine.IQ3_XS.gguf b/Qwen2-7B-Instruct-Refine.IQ3_XS.gguf new file mode 100644 index 0000000..891e88e --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94ada543edab27cb3283aef5d86b85d9b4f8fa7f1ae41c2449cfe3dc03bb34c1 +size 3346254016 diff --git a/Qwen2-7B-Instruct-Refine.IQ4_XS.gguf b/Qwen2-7B-Instruct-Refine.IQ4_XS.gguf new file mode 100644 index 0000000..5202119 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1f11a6ae8fbaf9ecbef330da6b3ad5941499c0136088011f0de44604c29373 +size 4250296512 diff --git a/Qwen2-7B-Instruct-Refine.Q2_K.gguf b/Qwen2-7B-Instruct-Refine.Q2_K.gguf new file mode 100644 index 0000000..7e7fe52 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece67efef646b08c20a5db1e176e04a995a38ccb954e62faebf01cc81eaf8ed8 +size 3015938240 diff --git a/Qwen2-7B-Instruct-Refine.Q3_K_L.gguf b/Qwen2-7B-Instruct-Refine.Q3_K_L.gguf new file mode 100644 index 0000000..1ab74dc --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6f4f6dfd165418580a0daad1ada206747179006ad965d4a4e3956c6a15a377 +size 4088457408 diff --git a/Qwen2-7B-Instruct-Refine.Q3_K_M.gguf b/Qwen2-7B-Instruct-Refine.Q3_K_M.gguf new file mode 100644 index 0000000..4052102 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec28aedf9641ed343bed8b4973d93eeda9129fab6b8e075ea6d3fe5c4bb56d5 +size 3808389312 diff --git a/Qwen2-7B-Instruct-Refine.Q3_K_S.gguf b/Qwen2-7B-Instruct-Refine.Q3_K_S.gguf new file mode 100644 index 0000000..a21f440 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed6f9c6d79d0037c0469abbb1cc0daee6ef0119e99b3bf52e9358993a69f782 +size 3492366528 diff --git a/Qwen2-7B-Instruct-Refine.Q4_K_M.gguf b/Qwen2-7B-Instruct-Refine.Q4_K_M.gguf new file mode 100644 index 0000000..956d33b --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a903681e3c0dbaf3f4f9d38d7cd6064f3940c54dd9e72b1233c8a825d99f78 +size 4683071680 diff --git a/Qwen2-7B-Instruct-Refine.Q4_K_S.gguf b/Qwen2-7B-Instruct-Refine.Q4_K_S.gguf new file mode 100644 index 0000000..003772c --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafb459bbddbeb4c13e39dc48eca742dbd23f6d8df78439a373cb075ee0c8ad1 +size 4457767104 diff --git a/Qwen2-7B-Instruct-Refine.Q5_K_M.gguf b/Qwen2-7B-Instruct-Refine.Q5_K_M.gguf new file mode 100644 index 0000000..9c8c327 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb3471fe2a90990bf48da65cb506937f7b76a988ca5e160a173dcd4963d2ee5 +size 5444829376 diff --git a/Qwen2-7B-Instruct-Refine.Q5_K_S.gguf b/Qwen2-7B-Instruct-Refine.Q5_K_S.gguf new file mode 100644 index 0000000..e4a9246 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147ddb29310e9b71b2ef4458f2f371a47a84d0dc8a17a05e44a5072e7c447d07 +size 5315174592 diff --git a/Qwen2-7B-Instruct-Refine.Q6_K.gguf b/Qwen2-7B-Instruct-Refine.Q6_K.gguf new file mode 100644 index 0000000..13e4ee6 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b05a04061f79e51448e5445289822508da1bf2b3cb260da681c599118382a1 +size 6254196928 diff --git a/Qwen2-7B-Instruct-Refine.Q8_0.gguf b/Qwen2-7B-Instruct-Refine.Q8_0.gguf new file mode 100644 index 0000000..b2eb278 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f5807c45b39c776998f7469515632aa8dd76d9712b6776744c3ab194a68976 +size 8098523328 diff --git a/Qwen2-7B-Instruct-Refine.f16.gguf b/Qwen2-7B-Instruct-Refine.f16.gguf new file mode 100644 index 0000000..64cb383 --- /dev/null +++ b/Qwen2-7B-Instruct-Refine.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28461284d6badd67ba86f2a0a1840bc6691774e596d2fe7741044972a54838c2 +size 15237851328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a34bad4 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: alibaba-pai/Qwen2-7B-Instruct-Refine +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/alibaba-pai/Qwen2-7B-Instruct-Refine + + +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/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.IQ3_XS.gguf) | IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.IQ3_M.gguf) | IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-Refine-GGUF/resolve/main/Qwen2-7B-Instruct-Refine.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. + +