commit 0f4f41f29ed64f9b942ace197abc471eb6595547 Author: ModelHub XC Date: Sun May 10 06:05:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1262e5 --- /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 +QiMing-Holos-Plus-Qwen3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QiMing-Holos-Plus-Qwen3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QiMing-Holos-Plus-Qwen3-8B.IQ4_XS.gguf b/QiMing-Holos-Plus-Qwen3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..9b0cc6f --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282b1b8a3912e3270ef5f79c0ac8db4442355362dc15829438d5e08667aac3c0 +size 4593297056 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q2_K.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q2_K.gguf new file mode 100644 index 0000000..d4541cf --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f52ab6715287ad78aadb3a60fdf8afb6186d44235f806fc2d7fcc9966c20ed4 +size 3281733280 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q3_K_L.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..44c1d9c --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c5c41f5e8ea38d9cea1ae7737310766ef19a3c6b5a778bfea2c6413ee440427 +size 4431394464 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q3_K_M.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..29b2651 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d7b06c5664921e6a3bfeb4a4edc86c18d005b46e1403aab0ab6c81ce98b410 +size 4124161696 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q3_K_S.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..f2ade5c --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c79a3a7bcbe3850fb055b7a9d5301a4d1bb9b54fdcbcb4349ae1037124d24f +size 3769611936 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q4_K_M.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..70503b3 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ae6fc596e4f5b6024066116457c1b3151c229460a62589c4b93ecdd0e7fc18 +size 5027784352 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q4_K_S.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..680f211 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bc96007e237c75d217e0149bd8e8296b2124d76e451ac508aba169be06ad66 +size 4802012832 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q5_K_M.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..610ea16 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6735baf4d2cd806b059ffea5ec4a210e7f98dfa10141e4b2acbec0be86dcdd7 +size 5851113120 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q5_K_S.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..9079a85 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d8c97c8a8f5f0f707a08b62708600fa454c0c4ce9bb3dffb88f1d009bdd0c7 +size 5720762016 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q6_K.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q6_K.gguf new file mode 100644 index 0000000..c287f83 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6d5cca6a4b8f70fbc7691459556858ec3dfcad79d842de0f962a367da82697 +size 6725899936 diff --git a/QiMing-Holos-Plus-Qwen3-8B.Q8_0.gguf b/QiMing-Holos-Plus-Qwen3-8B.Q8_0.gguf new file mode 100644 index 0000000..1d955e2 --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3125d3aa6f2b3d0a0de235b9bd5deaf07b8d02c70fc7899918e3a184b953f3d8 +size 8709519008 diff --git a/QiMing-Holos-Plus-Qwen3-8B.f16.gguf b/QiMing-Holos-Plus-Qwen3-8B.f16.gguf new file mode 100644 index 0000000..ec8eafd --- /dev/null +++ b/QiMing-Holos-Plus-Qwen3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f9a264e61baaf974b5a24f17b57fde6fa4b1b7882eb388a9997faf6476ef20 +size 16388044448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fe70946 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: aifeifei798/QiMing-Holos-Plus-Qwen3-8B +language: +- zh +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen +- qwen3 +- unsloth +- qiming +- qiming-holos +- bagua +- decision-making +- strategic-analysis +- cognitive-architecture +- chat +- lora +- philosophy-driven-ai +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aifeifei798/QiMing-Holos-Plus-Qwen3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QiMing-Holos-Plus-Qwen3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-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/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QiMing-Holos-Plus-Qwen3-8B-GGUF/resolve/main/QiMing-Holos-Plus-Qwen3-8B.f16.gguf) | f16 | 16.5 | 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. + +