commit 15e981ea764587c264be6d120c32382ef249cc6c Author: ModelHub XC Date: Mon Jun 15 00:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MegaSciMoE-1.2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a73ccd9 --- /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 +MegaSciMoE-1.2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MegaSciMoE-1.2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MegaSciMoE-1.2B.IQ4_XS.gguf b/MegaSciMoE-1.2B.IQ4_XS.gguf new file mode 100644 index 0000000..8f51e59 --- /dev/null +++ b/MegaSciMoE-1.2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b7f21b39c0451bfbbd29c1718757500a7aa2d1ae65c13e23996526c08893d5 +size 668618464 diff --git a/MegaSciMoE-1.2B.Q2_K.gguf b/MegaSciMoE-1.2B.Q2_K.gguf new file mode 100644 index 0000000..57c99e0 --- /dev/null +++ b/MegaSciMoE-1.2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d61218144af714f863d967d6e390fc3f7a3e5ef843176de1b4a8a5b1d25893 +size 483397344 diff --git a/MegaSciMoE-1.2B.Q3_K_L.gguf b/MegaSciMoE-1.2B.Q3_K_L.gguf new file mode 100644 index 0000000..508b605 --- /dev/null +++ b/MegaSciMoE-1.2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688c51d743064627d4850b6c8bf2f87c2244dd183c8d9b24dcb8cb3c08e49f8f +size 635473632 diff --git a/MegaSciMoE-1.2B.Q3_K_M.gguf b/MegaSciMoE-1.2B.Q3_K_M.gguf new file mode 100644 index 0000000..5f274d6 --- /dev/null +++ b/MegaSciMoE-1.2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cf8aee8a41a54e7aab34028e0928d167f24c3a72d9451bcc6ccf30acaecd25 +size 600346336 diff --git a/MegaSciMoE-1.2B.Q3_K_S.gguf b/MegaSciMoE-1.2B.Q3_K_S.gguf new file mode 100644 index 0000000..bff8ae3 --- /dev/null +++ b/MegaSciMoE-1.2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24da209b4cacb7ff672ca7b7d51964c7157655155c0cfd58cc11cc81a85854a1 +size 558157536 diff --git a/MegaSciMoE-1.2B.Q4_K_M.gguf b/MegaSciMoE-1.2B.Q4_K_M.gguf new file mode 100644 index 0000000..9c54d1d --- /dev/null +++ b/MegaSciMoE-1.2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3083a64e858e1fe7d0723e5badc76351426a5afe6e000a7cd17e11a2c552a60d +size 730894048 diff --git a/MegaSciMoE-1.2B.Q4_K_S.gguf b/MegaSciMoE-1.2B.Q4_K_S.gguf new file mode 100644 index 0000000..0114776 --- /dev/null +++ b/MegaSciMoE-1.2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f0cb1309baf380c8832b25f602ee600fe1ba3c0f10ce8dc41fcabbed48ef34 +size 700468960 diff --git a/MegaSciMoE-1.2B.Q5_K_M.gguf b/MegaSciMoE-1.2B.Q5_K_M.gguf new file mode 100644 index 0000000..fef86c3 --- /dev/null +++ b/MegaSciMoE-1.2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e4099e849e5e8ffc4f1da406fad1020025cae08cb440d6dc48215c855eb0314 +size 843353824 diff --git a/MegaSciMoE-1.2B.Q5_K_S.gguf b/MegaSciMoE-1.2B.Q5_K_S.gguf new file mode 100644 index 0000000..858239f --- /dev/null +++ b/MegaSciMoE-1.2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdce894510ea30857af84b7c4e8edae58e9ae88dcd9ab5058ca3f54e19206464 +size 825249504 diff --git a/MegaSciMoE-1.2B.Q6_K.gguf b/MegaSciMoE-1.2B.Q6_K.gguf new file mode 100644 index 0000000..58e08a7 --- /dev/null +++ b/MegaSciMoE-1.2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91981d884cbfffada56473d0ed118706fd88cf938ab93b83ea400c38a45010f +size 962842336 diff --git a/MegaSciMoE-1.2B.Q8_0.gguf b/MegaSciMoE-1.2B.Q8_0.gguf new file mode 100644 index 0000000..5b41f6d --- /dev/null +++ b/MegaSciMoE-1.2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e05572549bd55c379040f2de1f77f92769f42ea10df7573d6e20f7a7a1ddea +size 1246252768 diff --git a/MegaSciMoE-1.2B.f16.gguf b/MegaSciMoE-1.2B.f16.gguf new file mode 100644 index 0000000..a509629 --- /dev/null +++ b/MegaSciMoE-1.2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601f4e268f2e1522ca66aa42d5b784881ae7bea4216fd9f60c3b49462f53ee0f +size 2343325408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6ba3419 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: yasserrmd/MegaSciMoE-1.2B +datasets: +- MegaScience/MegaScience +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- lfm2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yasserrmd/MegaSciMoE-1.2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MegaSciMoE-1.2B-GGUF).*** + +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/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q2_K.gguf) | Q2_K | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MegaSciMoE-1.2B-GGUF/resolve/main/MegaSciMoE-1.2B.f16.gguf) | f16 | 2.4 | 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. + +