commit 883a0f70a3cc62696599ed19ad57d310ee022660 Author: ModelHub XC Date: Thu Jul 16 15:14:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..665cbb0 --- /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 +Qwen2-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-1.5B-Instruct.IQ3_M.gguf b/Qwen2-1.5B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..7cc0406 --- /dev/null +++ b/Qwen2-1.5B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b454f860c38d3b76101ebd7c385f6a9e9a0a9a97789b4eefa1cc91e544299f +size 776661536 diff --git a/Qwen2-1.5B-Instruct.IQ3_S.gguf b/Qwen2-1.5B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..f1b9faa --- /dev/null +++ b/Qwen2-1.5B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb933ba83dc192f3f8b00bd0f1118124d324b98e240d939125d9c6c668c5d23 +size 762404384 diff --git a/Qwen2-1.5B-Instruct.IQ3_XS.gguf b/Qwen2-1.5B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..23326ac --- /dev/null +++ b/Qwen2-1.5B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74bd85d5a986a8fc36eb5a6d2e1a7ee2380aedd5889e29750cfda448d179cb7 +size 731696672 diff --git a/Qwen2-1.5B-Instruct.IQ4_XS.gguf b/Qwen2-1.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..cd44f62 --- /dev/null +++ b/Qwen2-1.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57d468f4fa60b3598c4c0b40834867c3989f845625df1acabb3f8648c419487 +size 902180384 diff --git a/Qwen2-1.5B-Instruct.Q2_K.gguf b/Qwen2-1.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..84b078f --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be465ce5faa98eaad3d46403b85b4574b4188084679caebea4bd8e3fefecc662 +size 676302368 diff --git a/Qwen2-1.5B-Instruct.Q3_K_L.gguf b/Qwen2-1.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..b9ad3b9 --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:799c02944beef25242454534163c98d7faeb10615c470315fc99b1a06b74c7dd +size 880160288 diff --git a/Qwen2-1.5B-Instruct.Q3_K_M.gguf b/Qwen2-1.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..48c57fc --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24f6f54c21ffd9e895281464976262ec26c083ce9c6d2138e2b541f8464f7ba +size 824176160 diff --git a/Qwen2-1.5B-Instruct.Q3_K_S.gguf b/Qwen2-1.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..0444a50 --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2b13a4784062a36f52c4a6a58f1631cb31bc530a34569d880934af9b9a4c7b +size 760942112 diff --git a/Qwen2-1.5B-Instruct.Q4_K_M.gguf b/Qwen2-1.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..a00e418 --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c7231ead04221e9983fc813372ca7aaa6a45b905ee97af9f202014e443b656 +size 986045984 diff --git a/Qwen2-1.5B-Instruct.Q4_K_S.gguf b/Qwen2-1.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..d9d157c --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6c9fa09981c094c041633f35a3ff04dc41145c05eb784c8786007c5770f9f35 +size 940310048 diff --git a/Qwen2-1.5B-Instruct.Q5_K_M.gguf b/Qwen2-1.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8e8ed87 --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cf5c47d64cac4cdcba37bcbb376301c969340b5b8ae410b99fe0592c83b54bf +size 1125047840 diff --git a/Qwen2-1.5B-Instruct.Q5_K_S.gguf b/Qwen2-1.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..f52a8b3 --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ce424a08818d76e9eb8acf508f29847ca59026c46ab4b6a0702f2d375f1413 +size 1098726944 diff --git a/Qwen2-1.5B-Instruct.Q6_K.gguf b/Qwen2-1.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..d96825e --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f184cb35d74a1e49e847c2437591a440359b1e627b08d29b9343779a82ee3b9 +size 1272737312 diff --git a/Qwen2-1.5B-Instruct.Q8_0.gguf b/Qwen2-1.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..97f37d8 --- /dev/null +++ b/Qwen2-1.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7e149cbc5a7f323f46ab5086a5418d7c5bf7b628419d0c30915868f7debaad +size 1646570528 diff --git a/Qwen2-1.5B-Instruct.f16.gguf b/Qwen2-1.5B-Instruct.f16.gguf new file mode 100644 index 0000000..e7e8191 --- /dev/null +++ b/Qwen2-1.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252dcc0202bd89eab3432f39178a5dcafdfd6f27e7bd8161820d7ceabbf73fcf +size 3093666848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..185b44b --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen2-1.5B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2-1.5B-Instruct + + +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/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.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. + +