commit c599c1f5196da0c841d98874f0eb81b068dfb958 Author: ModelHub XC Date: Thu May 7 09:21:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/zen4-mini-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ea7afd --- /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 +zen4-mini.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +zen4-mini.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1aa892b --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: zenlm/zen4-mini +language: +- en +- zh +- ja +- ko +- fr +- de +- es +- pt +- ru +- ar +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- zen4 +- zenlm +- hanzo +- frontier-ai +- open-weight +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zenlm/zen4-mini + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#zen4-mini-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/zen4-mini-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/zen4-mini-GGUF/resolve/main/zen4-mini.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/zen4-mini-GGUF/resolve/main/zen4-mini.f16.gguf) | f16 | 8.2 | 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/zen4-mini.IQ4_XS.gguf b/zen4-mini.IQ4_XS.gguf new file mode 100644 index 0000000..15fc450 --- /dev/null +++ b/zen4-mini.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab720f035bf04d67a89b535247ca9c280bfbd93f972f2af5034edd09e9988e2d +size 2286316800 diff --git a/zen4-mini.Q2_K.gguf b/zen4-mini.Q2_K.gguf new file mode 100644 index 0000000..bd9549f --- /dev/null +++ b/zen4-mini.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4d37996a4139e804316bbcfcd0e542c5239f15e36bb65fba0e3575b20d5e4a +size 1669500160 diff --git a/zen4-mini.Q3_K_L.gguf b/zen4-mini.Q3_K_L.gguf new file mode 100644 index 0000000..a7d84ed --- /dev/null +++ b/zen4-mini.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb1c5c71c18fd7dc28ee936a8dbb5b62fdd14ff67a7483a24d8fefb834d3068 +size 2239786240 diff --git a/zen4-mini.Q3_K_M.gguf b/zen4-mini.Q3_K_M.gguf new file mode 100644 index 0000000..4a03245 --- /dev/null +++ b/zen4-mini.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f4d1ef845405c3cc4e2e06e6909ab8a53ca16687afc2af990784c3d53a1976 +size 2075618560 diff --git a/zen4-mini.Q3_K_S.gguf b/zen4-mini.Q3_K_S.gguf new file mode 100644 index 0000000..45da690 --- /dev/null +++ b/zen4-mini.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905f0d6c226eaf64dbab91acd6c0432ab8a1efc14033d2e39f1c49540175bc8b +size 1886997760 diff --git a/zen4-mini.Q4_K_M.gguf b/zen4-mini.Q4_K_M.gguf new file mode 100644 index 0000000..22dbf0b --- /dev/null +++ b/zen4-mini.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4937325449d91b2df4d54a77f3aa8e53da74cf870d9cf74de28c2718606a7616 +size 2497281280 diff --git a/zen4-mini.Q4_K_S.gguf b/zen4-mini.Q4_K_S.gguf new file mode 100644 index 0000000..d94fd30 --- /dev/null +++ b/zen4-mini.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da51f21d9997d402265e19fcd478143042c66a608e9dfa44b49bc3e2cd6fe2c +size 2383310080 diff --git a/zen4-mini.Q5_K_M.gguf b/zen4-mini.Q5_K_M.gguf new file mode 100644 index 0000000..43e0278 --- /dev/null +++ b/zen4-mini.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7cea50f088c23255f7dc6c41c75cbcc17dea3cfbd228ac425c005cca2b3756 +size 2889514240 diff --git a/zen4-mini.Q5_K_S.gguf b/zen4-mini.Q5_K_S.gguf new file mode 100644 index 0000000..d3d5158 --- /dev/null +++ b/zen4-mini.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e244999b00ec3ca665ed22b1be50c9973eae98154b1bf0985ffd2eb3f0f93e37 +size 2823712000 diff --git a/zen4-mini.Q6_K.gguf b/zen4-mini.Q6_K.gguf new file mode 100644 index 0000000..7037382 --- /dev/null +++ b/zen4-mini.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb9c550621479cb8b3daedec18e486d59cedca9f5675873613dc72a156d3d3e +size 3306261760 diff --git a/zen4-mini.Q8_0.gguf b/zen4-mini.Q8_0.gguf new file mode 100644 index 0000000..a08da81 --- /dev/null +++ b/zen4-mini.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eafc13cb34e95d138be08b55cd5ed46d5b395bd15104220b4669231d6248aa64 +size 4280405760 diff --git a/zen4-mini.f16.gguf b/zen4-mini.f16.gguf new file mode 100644 index 0000000..2059259 --- /dev/null +++ b/zen4-mini.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7c62928b5dfec2aac603bcb49f309ec6a50215bab77c930f5c79b1bab28ee21 +size 8051285760