commit 74af8c5a10e3475db136e445b5f1a9e128d1f4b6 Author: ModelHub XC Date: Tue Jun 2 16:31:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5faba01 --- /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 +Cetus-Qwen3_4B-GeneralThought.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cetus-Qwen3_4B-GeneralThought.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cetus-Qwen3_4B-GeneralThought.IQ4_XS.gguf b/Cetus-Qwen3_4B-GeneralThought.IQ4_XS.gguf new file mode 100644 index 0000000..deddebb --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3a77f8f3e829c9e620bc10b5bc116c7c893d202ef6a139651d685c7c35092e +size 2286317472 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q2_K.gguf b/Cetus-Qwen3_4B-GeneralThought.Q2_K.gguf new file mode 100644 index 0000000..07653a8 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0e6f208888097d8b8ebaa2288f2110b6317e7518a4833752efd9374ab150a3 +size 1669500832 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q3_K_L.gguf b/Cetus-Qwen3_4B-GeneralThought.Q3_K_L.gguf new file mode 100644 index 0000000..4c38c9c --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4b676ce3d168802cdf708c1e41fc93e72f0c7c1f188b8b2d391b902aac2073 +size 2239786912 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q3_K_M.gguf b/Cetus-Qwen3_4B-GeneralThought.Q3_K_M.gguf new file mode 100644 index 0000000..e49fba7 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbdb2a5b90852bd070777bf91bd4e5fc48e85cb5faa6cd2f15abdd8aaa40d2f +size 2075619232 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q3_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.Q3_K_S.gguf new file mode 100644 index 0000000..3a3320e --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5ca3b78452cf874a7a2c030abf55c641764405bbfcc33b29b1c97950c2f5e0 +size 1886998432 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q4_K_M.gguf b/Cetus-Qwen3_4B-GeneralThought.Q4_K_M.gguf new file mode 100644 index 0000000..ebed3e4 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97871e62e8ff98d9c082ec83eb533a827957ea04a461854c2c85ce0b1e53ebdd +size 2497281952 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q4_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.Q4_K_S.gguf new file mode 100644 index 0000000..21305a8 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbdad5f377d544926965f23ce2591e658b0c0bb837ddcdb123ebf358982ae0ce +size 2383310752 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q5_K_M.gguf b/Cetus-Qwen3_4B-GeneralThought.Q5_K_M.gguf new file mode 100644 index 0000000..6cec6ce --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba75f4d159419b6df5f227d80a9721f764301a9440dc13623afeb9659d54c39f +size 2889514912 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q5_K_S.gguf b/Cetus-Qwen3_4B-GeneralThought.Q5_K_S.gguf new file mode 100644 index 0000000..1f4865e --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573d3d9af75438d6315f2809e2dfa5846fd20675f408f5418b6252aef52ddef1 +size 2823712672 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q6_K.gguf b/Cetus-Qwen3_4B-GeneralThought.Q6_K.gguf new file mode 100644 index 0000000..fab33fc --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728dd184936edf5c4eedd83f844221e23200e48f0edbb6251a2a3719967f7b14 +size 3306262432 diff --git a/Cetus-Qwen3_4B-GeneralThought.Q8_0.gguf b/Cetus-Qwen3_4B-GeneralThought.Q8_0.gguf new file mode 100644 index 0000000..171e514 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d640506aceb66579d81137ea3380c142d6b5370132d4a8c8603040683687cee +size 4280406432 diff --git a/Cetus-Qwen3_4B-GeneralThought.f16.gguf b/Cetus-Qwen3_4B-GeneralThought.f16.gguf new file mode 100644 index 0000000..9c4d0e6 --- /dev/null +++ b/Cetus-Qwen3_4B-GeneralThought.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6707a9d6a2c06f249e363039f8bccbecda8d3d180c8f9cd5636117b18dc6f1a6 +size 8051286432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dea26f3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: prithivMLmods/Cetus-Qwen3_4B-GeneralThought +datasets: +- GeneralReasoning/GeneralThought-430K +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- text-generation-inference +- code +- math +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Cetus-Qwen3_4B-GeneralThought + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cetus-Qwen3_4B-GeneralThought-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-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/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cetus-Qwen3_4B-GeneralThought-GGUF/resolve/main/Cetus-Qwen3_4B-GeneralThought.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. + +