commit b1b4a45eb6fb306eb12073b48e97964ad09fd01d Author: ModelHub XC Date: Sat Oct 3 15:33:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6729b1 --- /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 +Summary-Qwen2.5-1.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Summary-Qwen2.5-1.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f233cfa --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: jester6136/Summary-Qwen2.5-1.5B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/jester6136/Summary-Qwen2.5-1.5B-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/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Summary-Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Summary-Qwen2.5-1.5B-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. + + diff --git a/Summary-Qwen2.5-1.5B-Instruct.IQ4_XS.gguf b/Summary-Qwen2.5-1.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..31e0a4c --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cfaa21a84c7a6ee9c257ba18b8773cf31b40c12d80e1f52a32784ce0b26521 +size 902183456 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q2_K.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..e5a2520 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d333eabf3424136eee46a688feeb95e16a33d3b6d191b18c47ac87f6fbc2a12 +size 676305440 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q3_K_L.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..a32268d --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc3355a3f3e777a764289d10f499e90c6e6b3acef5fea71a6d272df66f12b2c +size 880163360 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q3_K_M.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..d919885 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48659c65ae506aab3fe40f278ce7c7718d6ca94e15c82cd9c5f14e1f567fa2d1 +size 824179232 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q3_K_S.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bb0222d --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af72006ea2833ebfe36655fe88c3066f7e4b89c6703cffd5b904df29d932fc40 +size 760945184 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q4_K_M.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7a17ff8 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db75511999709929e6f245b899cfa6e6ee656a8ca773951242e4e729b24f94e +size 986049056 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q4_K_S.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..fc43a35 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ed3112d99b927c9a837ab32c459b21fd2fdbd78ffed720a19f412fba4fdeff +size 940313120 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q5_K_M.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..70fbc56 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80af38ad3e4ec90dceb286c3468879b7b864c26b3051e58f0e78c114045e5f6 +size 1125050912 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q5_K_S.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..ee64132 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a21d9ef8d4a4d192897caaf0ecf3265c8b08fdb7abab3bfba1fc67b53a2a59 +size 1098730016 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q6_K.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..cbd00f0 --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4315822f873f190e3b9954c152625dab455ff84524a813021ef675bdc9445c24 +size 1272740384 diff --git a/Summary-Qwen2.5-1.5B-Instruct.Q8_0.gguf b/Summary-Qwen2.5-1.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..3ad917d --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364a8927832fbf2b9d54aafa0ac87e09b44e6e93aae3a9c7b8da255519f69a56 +size 1646573600 diff --git a/Summary-Qwen2.5-1.5B-Instruct.f16.gguf b/Summary-Qwen2.5-1.5B-Instruct.f16.gguf new file mode 100644 index 0000000..c088bfd --- /dev/null +++ b/Summary-Qwen2.5-1.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6593464a9d35e97dd649ef91ddb50c9dc87b56b6cbba230f8c636962520ef058 +size 3093669920