commit 89f4f60e8ffc066667f9289f7538018a6080d5b1 Author: ModelHub XC Date: Wed May 27 19:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..802cada --- /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 +SmolLM2-moe-8x135M-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-moe-8x135M-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa07343 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: legionlm/SmolLM2-moe-8x135M-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/legionlm/SmolLM2-moe-8x135M-Instruct + + +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/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q6_K.gguf) | Q6_K | 0.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-moe-8x135M-Instruct-GGUF/resolve/main/SmolLM2-moe-8x135M-Instruct.f16.gguf) | f16 | 1.5 | 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. + + diff --git a/SmolLM2-moe-8x135M-Instruct.IQ4_XS.gguf b/SmolLM2-moe-8x135M-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..4fa1e0d --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31aef57075ec735be18c3d0487a7f57022030d382670ae8b342f3268165e3faa +size 423603456 diff --git a/SmolLM2-moe-8x135M-Instruct.Q2_K.gguf b/SmolLM2-moe-8x135M-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6f7d84d --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e8e8316d21073bc6e3f7f17054891711809e71b49ce094453606e554011a94 +size 398720256 diff --git a/SmolLM2-moe-8x135M-Instruct.Q3_K_L.gguf b/SmolLM2-moe-8x135M-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..00ebd27 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb10af1b119695801d70a13646f35e60bf3e34d8b38d673118bc63cea8fa024 +size 451597056 diff --git a/SmolLM2-moe-8x135M-Instruct.Q3_K_M.gguf b/SmolLM2-moe-8x135M-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0901105 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89392be425902146ac7e6233a4958f1ab61f693ab2c699cb1d3e4d91b3944c9e +size 427805952 diff --git a/SmolLM2-moe-8x135M-Instruct.Q3_K_S.gguf b/SmolLM2-moe-8x135M-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..f1784b7 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e5bdab7c82bbe0012ac9e8cb47685f8467d4f484c043b363a00b7e64d3616ce +size 398720256 diff --git a/SmolLM2-moe-8x135M-Instruct.Q4_K_M.gguf b/SmolLM2-moe-8x135M-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7f4e012 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa2efa0ce61db3e860c41d1ab21d5c5b02809b43b91d9eabbbb3f964c82743f +size 510335232 diff --git a/SmolLM2-moe-8x135M-Instruct.Q4_K_S.gguf b/SmolLM2-moe-8x135M-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..a657111 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ad9fb72564c4c0222f2ccb881756c5efbb700d91e2fc0727f4fb2f28b89921 +size 487442688 diff --git a/SmolLM2-moe-8x135M-Instruct.Q5_K_M.gguf b/SmolLM2-moe-8x135M-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a866290 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7475ba02cf34297af41cd183e240c00e4843677804ae184ee0ed873e80235afc +size 553424640 diff --git a/SmolLM2-moe-8x135M-Instruct.Q5_K_S.gguf b/SmolLM2-moe-8x135M-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..ef69b6c --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79afb873b1eb002364070c4b5ecc3daa9bde6af4d62e26b72037fb4baebdc1bd +size 540264192 diff --git a/SmolLM2-moe-8x135M-Instruct.Q6_K.gguf b/SmolLM2-moe-8x135M-Instruct.Q6_K.gguf new file mode 100644 index 0000000..2b50be3 --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc993f2345193eb9074856fdf9d13a9e00c238730e2e73923619b6520f49a516 +size 716243712 diff --git a/SmolLM2-moe-8x135M-Instruct.Q8_0.gguf b/SmolLM2-moe-8x135M-Instruct.Q8_0.gguf new file mode 100644 index 0000000..020b42a --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c771538835a3d59cccdcfd84b35170e447a238786243221cedc02121914459a4 +size 767668992 diff --git a/SmolLM2-moe-8x135M-Instruct.f16.gguf b/SmolLM2-moe-8x135M-Instruct.f16.gguf new file mode 100644 index 0000000..ae8cceb --- /dev/null +++ b/SmolLM2-moe-8x135M-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426cf88c8616145f14b691fb100cc85c29ba80379ddfa4def9b16d87eb6514e5 +size 1442833152