commit 0541effcbfea4a0decc764e7a8a31df90255e501 Author: ModelHub XC Date: Fri Jun 26 16:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-1_8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1dde2b8 --- /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-1_8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-1_8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-1_8B.IQ4_XS.gguf b/Qwen-1_8B.IQ4_XS.gguf new file mode 100644 index 0000000..4f05c5b --- /dev/null +++ b/Qwen-1_8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4457325619ef9dea90929463493eebd720b5d5458b4059ef7222d45d4a09153 +size 1087356416 diff --git a/Qwen-1_8B.Q2_K.gguf b/Qwen-1_8B.Q2_K.gguf new file mode 100644 index 0000000..c8c814c --- /dev/null +++ b/Qwen-1_8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c56a791474e64f3384bf11d7ad5aaeb41c7d45f1d0ce6fd7a872c9e93ba0af5 +size 836341248 diff --git a/Qwen-1_8B.Q3_K_L.gguf b/Qwen-1_8B.Q3_K_L.gguf new file mode 100644 index 0000000..a52c971 --- /dev/null +++ b/Qwen-1_8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7c11882734332fce96aa70e39dae55e8a8d03a4480f303be562be36c098f82a +size 1070351872 diff --git a/Qwen-1_8B.Q3_K_M.gguf b/Qwen-1_8B.Q3_K_M.gguf new file mode 100644 index 0000000..fef571f --- /dev/null +++ b/Qwen-1_8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7815b0f8e532fe9f7a12086dc1b25641793ecbcdc7d4ff28164e47e8398b76a2 +size 1041565184 diff --git a/Qwen-1_8B.Q3_K_S.gguf b/Qwen-1_8B.Q3_K_S.gguf new file mode 100644 index 0000000..16dc1fa --- /dev/null +++ b/Qwen-1_8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dfe0c3ec741a2c93febdbcbab2eb9afb89b575bfe2688422b4d194f33617ac4 +size 953566720 diff --git a/Qwen-1_8B.Q4_K_M.gguf b/Qwen-1_8B.Q4_K_M.gguf new file mode 100644 index 0000000..eeb84e6 --- /dev/null +++ b/Qwen-1_8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada2fe771b84a75130e295e80acc05ae2de4d44763ff7fd351def77d3d3e9648 +size 1242521088 diff --git a/Qwen-1_8B.Q4_K_S.gguf b/Qwen-1_8B.Q4_K_S.gguf new file mode 100644 index 0000000..4f6d157 --- /dev/null +++ b/Qwen-1_8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35aa5822e2e83d6657d9bedfc859ba2162e24590322a7bcc4e5071beb907adc1 +size 1156161024 diff --git a/Qwen-1_8B.Q5_K_M.gguf b/Qwen-1_8B.Q5_K_M.gguf new file mode 100644 index 0000000..122da28 --- /dev/null +++ b/Qwen-1_8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc1cb8194c4c899f4da5d94c82d5508f9f23c60283a842239beab5dc816acc2 +size 1410194944 diff --git a/Qwen-1_8B.Q5_K_S.gguf b/Qwen-1_8B.Q5_K_S.gguf new file mode 100644 index 0000000..8eaa702 --- /dev/null +++ b/Qwen-1_8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857b62b9438ed873de0e95a8a7f4fa599a20494b9a59f9df7db184f4f372e1d5 +size 1327816192 diff --git a/Qwen-1_8B.Q6_K.gguf b/Qwen-1_8B.Q6_K.gguf new file mode 100644 index 0000000..f4717a6 --- /dev/null +++ b/Qwen-1_8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14eebc073878e90bd2c206d2206413f2f111e281e47ec960b9c3821402270900 +size 1579021824 diff --git a/Qwen-1_8B.Q8_0.gguf b/Qwen-1_8B.Q8_0.gguf new file mode 100644 index 0000000..1b40f16 --- /dev/null +++ b/Qwen-1_8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eadc22e98d96426e0ed4cd6ce489b80f2ffb3e56d8d58a3703b4c1733f7c6a06 +size 1958299136 diff --git a/Qwen-1_8B.f16.gguf b/Qwen-1_8B.f16.gguf new file mode 100644 index 0000000..adeea13 --- /dev/null +++ b/Qwen-1_8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e8eb6dd104d0aacf3a0207efd4a8ffa4b11bbfb96ead701a64a4c58abb0088 +size 3680093696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd8a4a3 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Qwen/Qwen-1_8B +language: +- zh +- en +library_name: transformers +quantized_by: mradermacher +tags: +- qwen +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen-1_8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-1_8B-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-1_8B-GGUF/resolve/main/Qwen-1_8B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-1_8B-GGUF/resolve/main/Qwen-1_8B.f16.gguf) | f16 | 3.8 | 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. + +