commit 259da8e66fc2ecfee219ed53c9bf028e3e01c7a2 Author: ModelHub XC Date: Sun Apr 12 18:13:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d4b1ca0 --- /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 +SmollerLM2-360M-Instruct-Pruned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmollerLM2-360M-Instruct-Pruned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1fa3a19 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Fu01978/SmollerLM2-360M-Instruct-Pruned +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- pruned +- tiny-ml +- smollm +- research +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Fu01978/SmollerLM2-360M-Instruct-Pruned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmollerLM2-360M-Instruct-Pruned-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-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/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q6_K.gguf) | Q6_K | 0.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF/resolve/main/SmollerLM2-360M-Instruct-Pruned.f16.gguf) | f16 | 0.8 | 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/SmollerLM2-360M-Instruct-Pruned.IQ4_XS.gguf b/SmollerLM2-360M-Instruct-Pruned.IQ4_XS.gguf new file mode 100644 index 0000000..63b8c87 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9b9154f19c00e4193d40e495a4a1bf6c11d2efec5960df4090b15e9aca83c6 +size 224235008 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q2_K.gguf b/SmollerLM2-360M-Instruct-Pruned.Q2_K.gguf new file mode 100644 index 0000000..747756e --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022f3bc0bb7d5e18652762d3f264bae38f8815f604b77e5d5954976d86aee012 +size 222483968 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q3_K_L.gguf b/SmollerLM2-360M-Instruct-Pruned.Q3_K_L.gguf new file mode 100644 index 0000000..ae0da02 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d0e645aa05dfa9e7ddaed25e92aa4cf540466d5793ca1b57dd65f38d41ec6cd +size 243865088 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q3_K_M.gguf b/SmollerLM2-360M-Instruct-Pruned.Q3_K_M.gguf new file mode 100644 index 0000000..e56abb3 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194a7636c68fb1cf692e12c0d2f02f4e8fabefdf4857b9e45ba14e2b2fa067a6 +size 237068288 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q3_K_S.gguf b/SmollerLM2-360M-Instruct-Pruned.Q3_K_S.gguf new file mode 100644 index 0000000..cd6e9bc --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2dae60662d79550fe72b9fc6109ddebbc3d37fd66ff12f584a66e08a667f17f +size 222483968 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q4_K_M.gguf b/SmollerLM2-360M-Instruct-Pruned.Q4_K_M.gguf new file mode 100644 index 0000000..0e64c9c --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729a09e3fd8881d07c273d78e1207d32317650b48299b468c0cffcac93307b04 +size 276182528 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q4_K_S.gguf b/SmollerLM2-360M-Instruct-Pruned.Q4_K_S.gguf new file mode 100644 index 0000000..c00dbd7 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd53e3c121be4bf30004237bfd61247b6146e63bb083ccdf5f9f670e6389665 +size 260991488 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q5_K_M.gguf b/SmollerLM2-360M-Instruct-Pruned.Q5_K_M.gguf new file mode 100644 index 0000000..951a39b --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd05cf780391e52309061a89a1207be74805a57c9d8e1235210853fc917b48a +size 292464128 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q5_K_S.gguf b/SmollerLM2-360M-Instruct-Pruned.Q5_K_S.gguf new file mode 100644 index 0000000..09b6e1f --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c72456d5962af3f9bc3c4e3ba35d0211e12519744449a686f8be254aebf6dd +size 279254528 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q6_K.gguf b/SmollerLM2-360M-Instruct-Pruned.Q6_K.gguf new file mode 100644 index 0000000..bcbcb76 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c2b195e53edd819c4b145244b8c317216be3a6c85fe74d08594b01b8dd1280 +size 373872128 diff --git a/SmollerLM2-360M-Instruct-Pruned.Q8_0.gguf b/SmollerLM2-360M-Instruct-Pruned.Q8_0.gguf new file mode 100644 index 0000000..1193be1 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9937a824155ae7c3f0d63f85d9e5aabe6869bba06df91c3b6b3926bd36d4410b +size 373872128 diff --git a/SmollerLM2-360M-Instruct-Pruned.f16.gguf b/SmollerLM2-360M-Instruct-Pruned.f16.gguf new file mode 100644 index 0000000..f66beb1 --- /dev/null +++ b/SmollerLM2-360M-Instruct-Pruned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d18753d3022e277e9d1cce4d41c7421a9433fba21ba1b3ad697eb211b9a5a4 +size 701961728