commit 7d07f527cbb150ff1dd26187777d0d6193cf873d Author: ModelHub XC Date: Thu Jul 16 16:12:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f2591b5 --- /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 +Qwen-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-7B.IQ4_XS.gguf b/Qwen-7B.IQ4_XS.gguf new file mode 100644 index 0000000..0f4994f --- /dev/null +++ b/Qwen-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad4fa859728210afe592911f7ac63a3d1168599287bc369a5490f4470a98a2d +size 4318258592 diff --git a/Qwen-7B.Q2_K.gguf b/Qwen-7B.Q2_K.gguf new file mode 100644 index 0000000..53971a6 --- /dev/null +++ b/Qwen-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308c9509aecbb7a4754a4eefc79150ce6c84fcf1f3495825f7cebfdf3a6f809a +size 3049293216 diff --git a/Qwen-7B.Q3_K_L.gguf b/Qwen-7B.Q3_K_L.gguf new file mode 100644 index 0000000..41bc768 --- /dev/null +++ b/Qwen-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d659ac88b1fe8d4d86eb4f3782a0dabbfd56c718aa3816e11254cc8b96c7ebf +size 4293457312 diff --git a/Qwen-7B.Q3_K_M.gguf b/Qwen-7B.Q3_K_M.gguf new file mode 100644 index 0000000..865248d --- /dev/null +++ b/Qwen-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4454969bc2917ed7178ba5feb32c33a101dda29da3379ebbdc295dc72c12d87a +size 4057265568 diff --git a/Qwen-7B.Q3_K_S.gguf b/Qwen-7B.Q3_K_S.gguf new file mode 100644 index 0000000..6bd7a06 --- /dev/null +++ b/Qwen-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0f1702eda7e8fca29109455a7a119b9544cdca39714abdb9465b4fe1d45c81 +size 3569153440 diff --git a/Qwen-7B.Q4_K_M.gguf b/Qwen-7B.Q4_K_M.gguf new file mode 100644 index 0000000..011410a --- /dev/null +++ b/Qwen-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a09c200cc6c31c392860c050dd979000e6860e7ba825512e337c6e0dbeb980 +size 4899218848 diff --git a/Qwen-7B.Q4_K_S.gguf b/Qwen-7B.Q4_K_S.gguf new file mode 100644 index 0000000..eb825a9 --- /dev/null +++ b/Qwen-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a994cf0a0068b3d02eee26a075ae1677e25750800dbc74d9c46982eed6d84ba7 +size 4534445472 diff --git a/Qwen-7B.Q5_K_M.gguf b/Qwen-7B.Q5_K_M.gguf new file mode 100644 index 0000000..a3d6e2b --- /dev/null +++ b/Qwen-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5768883449c04f2b3b0996236a744f03a1f4b48cd2600d4af95474bab09450 +size 5708916128 diff --git a/Qwen-7B.Q5_K_S.gguf b/Qwen-7B.Q5_K_S.gguf new file mode 100644 index 0000000..217e3ad --- /dev/null +++ b/Qwen-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f659e0194a153dc1c895b9ba193a32bcc25179971a75bfc2426156d42267c7f +size 5399192992 diff --git a/Qwen-7B.Q6_K.gguf b/Qwen-7B.Q6_K.gguf new file mode 100644 index 0000000..034f1be --- /dev/null +++ b/Qwen-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e26b0f9ca7f41d8d80010ebce956d54e44c8a79cc59b2a7f92e827054d6e46 +size 6341940640 diff --git a/Qwen-7B.Q8_0.gguf b/Qwen-7B.Q8_0.gguf new file mode 100644 index 0000000..773437f --- /dev/null +++ b/Qwen-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc35eae60a7bf9d6b6f2034f4ab3e6e361570023444a625f4f78f36e6c5d82f +size 8211789216 diff --git a/Qwen-7B.f16.gguf b/Qwen-7B.f16.gguf new file mode 100644 index 0000000..b402068 --- /dev/null +++ b/Qwen-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2e02668ab0fbe12834dac0463ffce18d8ebfc90ff3ad2e08f00c3c0f16c2e6 +size 15449912736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..284475c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen-7B +language: +- zh +- en +library_name: transformers +license: other +license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT +license_name: tongyi-qianwen-license-agreement +quantized_by: mradermacher +tags: +- qwen +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-7B-i1-GGUF +## 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/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-GGUF/resolve/main/Qwen-7B.f16.gguf) | f16 | 15.5 | 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. + +