commit f6df436f05fa5d3baf93260b8315b8d092f6a0b1 Author: ModelHub XC Date: Tue May 19 02:26:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolLM2-360M-Instruct-FT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3992ba4 --- /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 +SmolLM2-360M-Instruct-FT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-360M-Instruct-FT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..db7e935 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: belyakoff/SmolLM2-360M-Instruct-FT +datasets: +- Vikhrmodels/GrandMaster-PRO-MAX +language: +- ru +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- rag +--- +## About + + + + + + +static quants of https://huggingface.co/belyakoff/SmolLM2-360M-Instruct-FT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmolLM2-360M-Instruct-FT-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/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q6_K.gguf) | Q6_K | 0.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-360M-Instruct-FT-GGUF/resolve/main/SmolLM2-360M-Instruct-FT.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/SmolLM2-360M-Instruct-FT.IQ4_XS.gguf b/SmolLM2-360M-Instruct-FT.IQ4_XS.gguf new file mode 100644 index 0000000..ab7b8c1 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d18c66d3b04fea86d4fdfd188740da891e7a0d7bc041daa1624e47110c462ed1 +size 228198048 diff --git a/SmolLM2-360M-Instruct-FT.Q2_K.gguf b/SmolLM2-360M-Instruct-FT.Q2_K.gguf new file mode 100644 index 0000000..dda5e4a --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38aa182114a4933374a4aa2c11a096442b41aefd0985e01cb74eda0cb0b72f92 +size 218674848 diff --git a/SmolLM2-360M-Instruct-FT.Q3_K_L.gguf b/SmolLM2-360M-Instruct-FT.Q3_K_L.gguf new file mode 100644 index 0000000..069fbb7 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf933c4423e0e3d3a453af414b5fcd20c1a7ba22573f92c3452fbf9fd5339eda +size 246322848 diff --git a/SmolLM2-360M-Instruct-FT.Q3_K_M.gguf b/SmolLM2-360M-Instruct-FT.Q3_K_M.gguf new file mode 100644 index 0000000..28b5edf --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dbd923b3c0d81dbe0f1a56c16362b94a9b27b68268483e1f0cc9c6e89dc5fac +size 234687648 diff --git a/SmolLM2-360M-Instruct-FT.Q3_K_S.gguf b/SmolLM2-360M-Instruct-FT.Q3_K_S.gguf new file mode 100644 index 0000000..6749969 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24505f8c6b6f68c5afc42d229b2800e32b1fe1b76059b8b7c2a68c5d5c92540c +size 218674848 diff --git a/SmolLM2-360M-Instruct-FT.Q4_K_M.gguf b/SmolLM2-360M-Instruct-FT.Q4_K_M.gguf new file mode 100644 index 0000000..046bea5 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e163ff7604be4e2ad950919aa52e4854f0fae12569939c492473c86e7b0b0ad +size 270591648 diff --git a/SmolLM2-360M-Instruct-FT.Q4_K_S.gguf b/SmolLM2-360M-Instruct-FT.Q4_K_S.gguf new file mode 100644 index 0000000..c8882a8 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09706f43d0e6be693621c8bbe20c27d397fdcbd0e58136fc7aad7f5ac8c6d1d4 +size 259916448 diff --git a/SmolLM2-360M-Instruct-FT.Q5_K_M.gguf b/SmolLM2-360M-Instruct-FT.Q5_K_M.gguf new file mode 100644 index 0000000..1e242c2 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b6de95ff8f6eabe1d8828c40e269d292f5083eb9d335621ea672ce05307085 +size 289945248 diff --git a/SmolLM2-360M-Instruct-FT.Q5_K_S.gguf b/SmolLM2-360M-Instruct-FT.Q5_K_S.gguf new file mode 100644 index 0000000..485923f --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469aa7b5f275d20ef42d0d0f9eb5acec953ccc80ac8219069774e355b0e499d8 +size 283186848 diff --git a/SmolLM2-360M-Instruct-FT.Q6_K.gguf b/SmolLM2-360M-Instruct-FT.Q6_K.gguf new file mode 100644 index 0000000..3c9428a --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe79076ded645ce8d201dbe6c53cd9e436f8f8b449faee89a45105b04d87d06 +size 367359648 diff --git a/SmolLM2-360M-Instruct-FT.Q8_0.gguf b/SmolLM2-360M-Instruct-FT.Q8_0.gguf new file mode 100644 index 0000000..e2fe95f --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e16d775140f3e96c885a0fc3fcdd83f5c6a3267c6ee1c8b7f2e5bca76354d4 +size 386406048 diff --git a/SmolLM2-360M-Instruct-FT.f16.gguf b/SmolLM2-360M-Instruct-FT.f16.gguf new file mode 100644 index 0000000..1595f68 --- /dev/null +++ b/SmolLM2-360M-Instruct-FT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fdb3d613129f7a223a808996ee470cc431dfc13cc3a2c6119063b06fe3757f +size 725554848