commit e6b15ac3394cf28982b658fb3ecb178479a41e9c Author: ModelHub XC Date: Thu May 7 00:56:43 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/SJT-Moe2x7.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a2eff8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +SJT-Moe2x7.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SJT-Moe2x7.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..575f14a --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Sakalti/SJT-Moe2x7.5B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- moe +--- +## About + + + + + + +static quants of https://huggingface.co/Sakalti/SJT-Moe2x7.5B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SJT-Moe2x7.5B-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/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q2_K.gguf) | Q2_K | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q3_K_S.gguf) | Q3_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q3_K_M.gguf) | Q3_K_M | 6.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q3_K_L.gguf) | Q3_K_L | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.IQ4_XS.gguf) | IQ4_XS | 7.4 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q4_K_S.gguf) | Q4_K_S | 7.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q4_K_M.gguf) | Q4_K_M | 8.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q5_K_S.gguf) | Q5_K_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q5_K_M.gguf) | Q5_K_M | 9.6 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q6_K.gguf) | Q6_K | 11.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SJT-Moe2x7.5B-GGUF/resolve/main/SJT-Moe2x7.5B.Q8_0.gguf) | Q8_0 | 14.3 | 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/SJT-Moe2x7.5B.IQ4_XS.gguf b/SJT-Moe2x7.5B.IQ4_XS.gguf new file mode 100644 index 0000000..d25b8eb --- /dev/null +++ b/SJT-Moe2x7.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289c6e14475c1772aa3f66166d53b00136cb44ab13cc748991eab23cad9e6f26 +size 7308061632 diff --git a/SJT-Moe2x7.5B.Q2_K.gguf b/SJT-Moe2x7.5B.Q2_K.gguf new file mode 100644 index 0000000..074b1b6 --- /dev/null +++ b/SJT-Moe2x7.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df809a1bd2ecdac13733d003b07e7b5c1984f200e07f31ffa519238f3410c4f +size 5039795136 diff --git a/SJT-Moe2x7.5B.Q3_K_L.gguf b/SJT-Moe2x7.5B.Q3_K_L.gguf new file mode 100644 index 0000000..cc8933a --- /dev/null +++ b/SJT-Moe2x7.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d04706e2bb64e5b685f05988688238491cf821897be6589b6f1336dbd7f241 +size 7034284992 diff --git a/SJT-Moe2x7.5B.Q3_K_M.gguf b/SJT-Moe2x7.5B.Q3_K_M.gguf new file mode 100644 index 0000000..60d7206 --- /dev/null +++ b/SJT-Moe2x7.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7d546cd3a98ef6ac5bcbb650ee2c6d433a9aa39e9e8fa13134dd39399dea97 +size 6513273792 diff --git a/SJT-Moe2x7.5B.Q3_K_S.gguf b/SJT-Moe2x7.5B.Q3_K_S.gguf new file mode 100644 index 0000000..14b6376 --- /dev/null +++ b/SJT-Moe2x7.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf0f8c5c1cbc414d155504f3f5cbf6c370e42736f3ff39a154682e4f51c21be +size 5921582016 diff --git a/SJT-Moe2x7.5B.Q4_K_M.gguf b/SJT-Moe2x7.5B.Q4_K_M.gguf new file mode 100644 index 0000000..9aa198e --- /dev/null +++ b/SJT-Moe2x7.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870f37a291eaef3593ae4beb6d6055e8975712316b57f485c08dc1d922547ded +size 8170187712 diff --git a/SJT-Moe2x7.5B.Q4_K_S.gguf b/SJT-Moe2x7.5B.Q4_K_S.gguf new file mode 100644 index 0000000..43126ea --- /dev/null +++ b/SJT-Moe2x7.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fcdc78ff011a8995c47442b360ddd1e967f7707100aad075c65aa536de3b54b +size 7702555584 diff --git a/SJT-Moe2x7.5B.Q5_K_M.gguf b/SJT-Moe2x7.5B.Q5_K_M.gguf new file mode 100644 index 0000000..e218d6a --- /dev/null +++ b/SJT-Moe2x7.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bd1be7a9ca4510a6d1f9ee6a2fa8e8636c604f92a524b9411087cf7788f3ca +size 9541725120 diff --git a/SJT-Moe2x7.5B.Q5_K_S.gguf b/SJT-Moe2x7.5B.Q5_K_S.gguf new file mode 100644 index 0000000..fe39e06 --- /dev/null +++ b/SJT-Moe2x7.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23642af88b341910d2c53164942231272cc8d8ef1e060c95abbda7ed8fa76a92 +size 9272667072 diff --git a/SJT-Moe2x7.5B.Q6_K.gguf b/SJT-Moe2x7.5B.Q6_K.gguf new file mode 100644 index 0000000..361e4e7 --- /dev/null +++ b/SJT-Moe2x7.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2500dfc9b963101f636f04ffb7e151f8a5661e554211c434f31fad186258a9a +size 10998983616 diff --git a/SJT-Moe2x7.5B.Q8_0.gguf b/SJT-Moe2x7.5B.Q8_0.gguf new file mode 100644 index 0000000..d032174 --- /dev/null +++ b/SJT-Moe2x7.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:526ed7264632e889c6565b0e55b91e8408a998b676c3aea2c6d1686011acc76c +size 14244490176