commit 703ca78079d81b78b003080bb6c480f11cd46928 Author: ModelHub XC Date: Mon Apr 27 04:52:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/StarlingMaths-12B-MoE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5de65d --- /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 +StarlingMaths-12B-MoE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +StarlingMaths-12B-MoE.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7be3cc --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: allknowingroger/StarlingMaths-12B-MoE +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- moe +- frankenmoe +- merge +- mergekit +- lazymergekit +- allknowingroger/StarlingMaxLimmy2-7B-slerp +- Kukedlc/NeuralMaths-Experiment-7b +--- +## About + + + + + + +static quants of https://huggingface.co/allknowingroger/StarlingMaths-12B-MoE + + +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/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q3_K_S.gguf) | Q3_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q3_K_L.gguf) | Q3_K_L | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.IQ4_XS.gguf) | IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q4_0_4_4.gguf) | Q4_0_4_4 | 7.4 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q4_K_M.gguf) | Q4_K_M | 7.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q5_K_S.gguf) | Q5_K_S | 9.0 | | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q5_K_M.gguf) | Q5_K_M | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q6_K.gguf) | Q6_K | 10.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/StarlingMaths-12B-MoE-GGUF/resolve/main/StarlingMaths-12B-MoE.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality | + +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/StarlingMaths-12B-MoE.IQ4_XS.gguf b/StarlingMaths-12B-MoE.IQ4_XS.gguf new file mode 100644 index 0000000..804575b --- /dev/null +++ b/StarlingMaths-12B-MoE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc71ecef59e7928101fc549d0d8123bc07abd40d3930ec61cf25d8184b7d772 +size 6976875136 diff --git a/StarlingMaths-12B-MoE.Q2_K.gguf b/StarlingMaths-12B-MoE.Q2_K.gguf new file mode 100644 index 0000000..95118ca --- /dev/null +++ b/StarlingMaths-12B-MoE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a853b4677bf38b41f3631749480539805f6b0c3b7d1a4512445684bfcfc2e27 +size 4760824448 diff --git a/StarlingMaths-12B-MoE.Q3_K_L.gguf b/StarlingMaths-12B-MoE.Q3_K_L.gguf new file mode 100644 index 0000000..4c6137c --- /dev/null +++ b/StarlingMaths-12B-MoE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17d6b2c4d89dd665a9cbe1b44403b99075042460fbefd07738f95b45ce227b4 +size 6729730688 diff --git a/StarlingMaths-12B-MoE.Q3_K_M.gguf b/StarlingMaths-12B-MoE.Q3_K_M.gguf new file mode 100644 index 0000000..0fbf297 --- /dev/null +++ b/StarlingMaths-12B-MoE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e33af5470c186bff4fbb4b7f2e3edbd80a3ba4c19645149842968df3f762f3af +size 6206491264 diff --git a/StarlingMaths-12B-MoE.Q3_K_S.gguf b/StarlingMaths-12B-MoE.Q3_K_S.gguf new file mode 100644 index 0000000..c2beacb --- /dev/null +++ b/StarlingMaths-12B-MoE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ad99e8b238ee20495c3ed0b95b82b90a4ca6b9e6cc93e21d00a8f72da8b129 +size 5587831424 diff --git a/StarlingMaths-12B-MoE.Q4_0_4_4.gguf b/StarlingMaths-12B-MoE.Q4_0_4_4.gguf new file mode 100644 index 0000000..0346189 --- /dev/null +++ b/StarlingMaths-12B-MoE.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152fa2e7c93396922858b5f4a5714feeaa959244e2c0530cf3e6b540843963e0 +size 7280863872 diff --git a/StarlingMaths-12B-MoE.Q4_K_M.gguf b/StarlingMaths-12B-MoE.Q4_K_M.gguf new file mode 100644 index 0000000..58a8604 --- /dev/null +++ b/StarlingMaths-12B-MoE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0393b0065fe40a42f9ecdcad51415a2e1c970b55682ea40f260722144e37c7c4 +size 7782607488 diff --git a/StarlingMaths-12B-MoE.Q4_K_S.gguf b/StarlingMaths-12B-MoE.Q4_K_S.gguf new file mode 100644 index 0000000..074e0e2 --- /dev/null +++ b/StarlingMaths-12B-MoE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9414b49ac3ed202be3a2fe583d0db92fd16cd446702828c8e44731a012713fe4 +size 7341681280 diff --git a/StarlingMaths-12B-MoE.Q5_K_M.gguf b/StarlingMaths-12B-MoE.Q5_K_M.gguf new file mode 100644 index 0000000..72ea7a8 --- /dev/null +++ b/StarlingMaths-12B-MoE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151c24ba3ef656ebe776e860a9b80a050a337030927e949fcc0ac7a3641e7d08 +size 9132780160 diff --git a/StarlingMaths-12B-MoE.Q5_K_S.gguf b/StarlingMaths-12B-MoE.Q5_K_S.gguf new file mode 100644 index 0000000..b9698fa --- /dev/null +++ b/StarlingMaths-12B-MoE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadf99902b8977923438ced00d11f303e073125d157fb892958f058ade264bc4 +size 8874306176 diff --git a/StarlingMaths-12B-MoE.Q6_K.gguf b/StarlingMaths-12B-MoE.Q6_K.gguf new file mode 100644 index 0000000..22a43b4 --- /dev/null +++ b/StarlingMaths-12B-MoE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a54559f902f13180bf93c7179beab95a18b52bc18991259acc86fda092f9eea +size 10567338624 diff --git a/StarlingMaths-12B-MoE.Q8_0.gguf b/StarlingMaths-12B-MoE.Q8_0.gguf new file mode 100644 index 0000000..5358b8b --- /dev/null +++ b/StarlingMaths-12B-MoE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba0428015460b757d90a51d7be5bdee31a7b51baa43c26c566af447b4d0c6c4 +size 13686377088