commit e6be9b5dace98854735159522b5c6085dff99c84 Author: ModelHub XC Date: Wed Jul 8 18:08:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CeptrixBeagle-12B-MoE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb4d4a3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +CeptrixBeagle-12B-MoE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CeptrixBeagle-12B-MoE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CeptrixBeagle-12B-MoE.IQ3_M.gguf b/CeptrixBeagle-12B-MoE.IQ3_M.gguf new file mode 100644 index 0000000..2de9103 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcaf8540abc0f6d1a1dd55a23e276b22bc18ff82b701c064f1793c6262eadfa5 +size 5739349120 diff --git a/CeptrixBeagle-12B-MoE.IQ3_S.gguf b/CeptrixBeagle-12B-MoE.IQ3_S.gguf new file mode 100644 index 0000000..dc508a5 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e73542b96c07a1b1d5d93bbef927aed162d391c9743043b54c1e36aca8d016 +size 5605655680 diff --git a/CeptrixBeagle-12B-MoE.IQ3_XS.gguf b/CeptrixBeagle-12B-MoE.IQ3_XS.gguf new file mode 100644 index 0000000..7a0f9ec --- /dev/null +++ b/CeptrixBeagle-12B-MoE.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc10e886a79d03c6e412587ae535d1589923d12bb3bc26d37b2a4473c5740d1 +size 5309957248 diff --git a/CeptrixBeagle-12B-MoE.IQ4_XS.gguf b/CeptrixBeagle-12B-MoE.IQ4_XS.gguf new file mode 100644 index 0000000..288a922 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56b0b184f2c949d006c30710f188921135eb2238d097a93e7ec143225629988 +size 6976873600 diff --git a/CeptrixBeagle-12B-MoE.Q2_K.gguf b/CeptrixBeagle-12B-MoE.Q2_K.gguf new file mode 100644 index 0000000..8b01400 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c91c83d797dd37097d34ff2b3d8007ab871d2bf2c7ebbe08900ff88b45d58f4 +size 4760822912 diff --git a/CeptrixBeagle-12B-MoE.Q3_K_L.gguf b/CeptrixBeagle-12B-MoE.Q3_K_L.gguf new file mode 100644 index 0000000..390a5e1 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd5111b38bddb8c31ffba81f847c0009d5f1c55f5f24365f66062bf007e9e31 +size 6729729152 diff --git a/CeptrixBeagle-12B-MoE.Q3_K_M.gguf b/CeptrixBeagle-12B-MoE.Q3_K_M.gguf new file mode 100644 index 0000000..0279aa0 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4a831f5bfee7db2763f5e98d7a5ec3143108f867c7ffffae0ff74d6cebea61 +size 6206489728 diff --git a/CeptrixBeagle-12B-MoE.Q3_K_S.gguf b/CeptrixBeagle-12B-MoE.Q3_K_S.gguf new file mode 100644 index 0000000..1bf0d06 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eecd81353a22e024c742fa409d2edfb1f28d2cd5e90582f8c6867bd194f24240 +size 5587829888 diff --git a/CeptrixBeagle-12B-MoE.Q4_K_M.gguf b/CeptrixBeagle-12B-MoE.Q4_K_M.gguf new file mode 100644 index 0000000..06f4638 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe0dae3c894be63087d079714e019a6b968b0fd9f53582e96e5f0131bef193e +size 7782605952 diff --git a/CeptrixBeagle-12B-MoE.Q4_K_S.gguf b/CeptrixBeagle-12B-MoE.Q4_K_S.gguf new file mode 100644 index 0000000..bd39393 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a623f7fad66784975f120342c59c4498c1ccadd61fc8dc47469b0d22c3d7559 +size 7341679744 diff --git a/CeptrixBeagle-12B-MoE.Q5_K_M.gguf b/CeptrixBeagle-12B-MoE.Q5_K_M.gguf new file mode 100644 index 0000000..ad2af11 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371b3909aea3223f311b9b6a257fe3adbcda6480a40ef0e415a9e028f5c2d2f0 +size 9132778624 diff --git a/CeptrixBeagle-12B-MoE.Q5_K_S.gguf b/CeptrixBeagle-12B-MoE.Q5_K_S.gguf new file mode 100644 index 0000000..1b144a7 --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43b45f203a5f2282750c17b278cb9601967e92be48ff4833d162150b9a0bba8 +size 8874304640 diff --git a/CeptrixBeagle-12B-MoE.Q6_K.gguf b/CeptrixBeagle-12B-MoE.Q6_K.gguf new file mode 100644 index 0000000..d90628f --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc54589ca78e72ed9e20b83d0cacdba888617ec59d13dc12c4f437fe8ab50b0f +size 10567337088 diff --git a/CeptrixBeagle-12B-MoE.Q8_0.gguf b/CeptrixBeagle-12B-MoE.Q8_0.gguf new file mode 100644 index 0000000..94ccc7b --- /dev/null +++ b/CeptrixBeagle-12B-MoE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3aea51740f76cbf68ad9470ac0bdea605b6875d4c01b7649bed75f226b5def +size 13686375552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..713a1fa --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: allknowingroger/CeptrixBeagle-12B-MoE +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- moe +- frankenmoe +- merge +- mergekit +- lazymergekit +- allknowingroger/NeuralCeptrix-7B-slerp +- paulml/OmniBeagleSquaredMBX-v3-7B +--- +## About + + + + + +static quants of https://huggingface.co/allknowingroger/CeptrixBeagle-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/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.IQ3_XS.gguf) | IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q3_K_S.gguf) | Q3_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.IQ3_S.gguf) | IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.IQ3_M.gguf) | IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q3_K_L.gguf) | Q3_K_L | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.IQ4_XS.gguf) | IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q4_K_M.gguf) | Q4_K_M | 7.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q5_K_S.gguf) | Q5_K_S | 9.0 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q5_K_M.gguf) | Q5_K_M | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-12B-MoE.Q6_K.gguf) | Q6_K | 10.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CeptrixBeagle-12B-MoE-GGUF/resolve/main/CeptrixBeagle-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. + +