commit 325a4c8e7de5662eee49d3166ac928de71668216 Author: ModelHub XC Date: Sun Jun 21 17:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-Wukong-0.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5711bfc --- /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 +Qwen1.5-Wukong-0.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-Wukong-0.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-Wukong-0.5B.IQ4_XS.gguf b/Qwen1.5-Wukong-0.5B.IQ4_XS.gguf new file mode 100644 index 0000000..e6566fd --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd37d1a8b7f346cab18995478071e88ebe4b917746487531a36ead6275e888b7 +size 299192128 diff --git a/Qwen1.5-Wukong-0.5B.Q2_K.gguf b/Qwen1.5-Wukong-0.5B.Q2_K.gguf new file mode 100644 index 0000000..973cb3e --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0158ec735b25681e961e18c642d22acf654d8bac49db396d56f2141c123ae6fa +size 247361344 diff --git a/Qwen1.5-Wukong-0.5B.Q3_K_L.gguf b/Qwen1.5-Wukong-0.5B.Q3_K_L.gguf new file mode 100644 index 0000000..54a071c --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2fa87f120db38b7df63a42d611ec676806b2efaccc735849430846d76ffee2 +size 297348928 diff --git a/Qwen1.5-Wukong-0.5B.Q3_K_M.gguf b/Qwen1.5-Wukong-0.5B.Q3_K_M.gguf new file mode 100644 index 0000000..ca26328 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fa91d04fa2d86fcbb8cbadb1906610e75ab2f2b02fee2f4e8cd628fb5df5d8 +size 283029312 diff --git a/Qwen1.5-Wukong-0.5B.Q3_K_S.gguf b/Qwen1.5-Wukong-0.5B.Q3_K_S.gguf new file mode 100644 index 0000000..69a7032 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3c134754342bdc26b5f295e50b339637d83584fec5d23c2d88da7d8cd4596b +size 266530624 diff --git a/Qwen1.5-Wukong-0.5B.Q4_K_M.gguf b/Qwen1.5-Wukong-0.5B.Q4_K_M.gguf new file mode 100644 index 0000000..6e6d735 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa0c3e20239830907f612c664272f36fb7e25f4d7f56548df247d0032c3ae34 +size 319639360 diff --git a/Qwen1.5-Wukong-0.5B.Q4_K_S.gguf b/Qwen1.5-Wukong-0.5B.Q4_K_S.gguf new file mode 100644 index 0000000..da1f7c6 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e914f3d155fa06b842a43be163ec0c5a16c7e393601a6892dc08737d49e25edb +size 309079872 diff --git a/Qwen1.5-Wukong-0.5B.Q5_K_M.gguf b/Qwen1.5-Wukong-0.5B.Q5_K_M.gguf new file mode 100644 index 0000000..68daf01 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90e6231c7ccaf3d592d5259fb94ef76e5f7ed01b8bd0da7679543f030483a0ca +size 352276288 diff --git a/Qwen1.5-Wukong-0.5B.Q5_K_S.gguf b/Qwen1.5-Wukong-0.5B.Q5_K_S.gguf new file mode 100644 index 0000000..576cb65 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9199a1b691ba9c38d29fb67000dda2eb1917ca96b46f5abe9588bf14868815e3 +size 346009408 diff --git a/Qwen1.5-Wukong-0.5B.Q6_K.gguf b/Qwen1.5-Wukong-0.5B.Q6_K.gguf new file mode 100644 index 0000000..89fae50 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c879074f32b51a23730956319c0341daf25f811d1fb161e51803adb115a06040 +size 386953024 diff --git a/Qwen1.5-Wukong-0.5B.Q8_0.gguf b/Qwen1.5-Wukong-0.5B.Q8_0.gguf new file mode 100644 index 0000000..ebc7417 --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e8fe8ca48e2fdbe615249270a76ce37721265df622937ef5bc164794731149 +size 499295040 diff --git a/Qwen1.5-Wukong-0.5B.f16.gguf b/Qwen1.5-Wukong-0.5B.f16.gguf new file mode 100644 index 0000000..0a4d62b --- /dev/null +++ b/Qwen1.5-Wukong-0.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4316ae9f5c01bdd125b181370eccbf5f56736760bdd7ce1283e300d648c2ac1 +size 934167360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8cb44cc --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: RESMPDEV/Qwen1.5-Wukong-0.5B +datasets: +- teknium/OpenHermes-2.5 +language: +- en +- zh +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE +license_name: tongyi-qianwen-research +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/RESMPDEV/Qwen1.5-Wukong-0.5B + + +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/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.IQ4_XS.gguf) | IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q6_K.gguf) | Q6_K | 0.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-Wukong-0.5B-GGUF/resolve/main/Qwen1.5-Wukong-0.5B.f16.gguf) | f16 | 1.0 | 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. + +