commit 72ff68d6b34e8bc72905b8cb5a9ea6f60605f852 Author: ModelHub XC Date: Wed Oct 7 11:53:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolLM2-1.7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bd9ab18 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +SmolLM2-1.7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b62eb09 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- safetensors +- onnx +- transformers.js +--- +## About + + + + + + +static quants of https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-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/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.1 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct.f16.gguf) | f16 | 3.5 | 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/SmolLM2-1.7B-Instruct.IQ4_XS.gguf b/SmolLM2-1.7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ff5e00b --- /dev/null +++ b/SmolLM2-1.7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3980b283fe8c5ae279736c5c0cd17db44be55c56de8fb35d496358afbca417 +size 948261952 diff --git a/SmolLM2-1.7B-Instruct.Q2_K.gguf b/SmolLM2-1.7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..899da1f --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:485780f1b430e784046a715f3c6ebcc6cb6884321943c855e762915e3a8e4d07 +size 674583616 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_L.gguf b/SmolLM2-1.7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1b8f9f0 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884f910b1daa03f634d0af6f7f6ac57ab23bb1784235416ad9437c263ebace0b +size 932533312 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_M.gguf b/SmolLM2-1.7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..6946dcc --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13165645925c83b4aa998552621fa411a01c4c25a32f95bf07eb008b721d9cab +size 860181568 diff --git a/SmolLM2-1.7B-Instruct.Q3_K_S.gguf b/SmolLM2-1.7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..3a85239 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c354d51e7531b6b550769822ea962f0ca4d653feb1f166b23e659134e24d50 +size 776819776 diff --git a/SmolLM2-1.7B-Instruct.Q4_0_4_4.gguf b/SmolLM2-1.7B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..3f74a18 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92fa61f82b58d3b7fdd0a02ae0ed6199b982631a452f045fac6b2f92265bf5a0 +size 990729280 diff --git a/SmolLM2-1.7B-Instruct.Q4_K_M.gguf b/SmolLM2-1.7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f9529a3 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a41959991ff89418c288727732c52e0a673e6c6eaf824553aeb8eb43445b355c +size 1055609920 diff --git a/SmolLM2-1.7B-Instruct.Q4_K_S.gguf b/SmolLM2-1.7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c49d7ed --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ad2e645265707b3b05471306e6eaaa1b63878844daeb8528538c5c5303ee65 +size 999117888 diff --git a/SmolLM2-1.7B-Instruct.Q5_K_M.gguf b/SmolLM2-1.7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..57a1be7 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e89e4ed3736198eecf097c5bcb3f40f7b57993caac8ab4e0d86c2e2c49bcdc +size 1225479232 diff --git a/SmolLM2-1.7B-Instruct.Q5_K_S.gguf b/SmolLM2-1.7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..104a37f --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df0af60055a690c9bdc3a88b09fa2e0ecb3e03b76dad2504c8cb902186c3264 +size 1192055872 diff --git a/SmolLM2-1.7B-Instruct.Q6_K.gguf b/SmolLM2-1.7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..ef79517 --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735c1da477c842d2925ccbcdd7040bc5c2164156786fe6acfcc191df502b5da4 +size 1405965376 diff --git a/SmolLM2-1.7B-Instruct.Q8_0.gguf b/SmolLM2-1.7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..e13f2ba --- /dev/null +++ b/SmolLM2-1.7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb483bcb3062dcb601b18ad5e1051ed4c961a7b87a1a4cb0c41753a0b204dea +size 1820415040 diff --git a/SmolLM2-1.7B-Instruct.f16.gguf b/SmolLM2-1.7B-Instruct.f16.gguf new file mode 100644 index 0000000..112e69e --- /dev/null +++ b/SmolLM2-1.7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a616ef779ff7087d29256d9e1198e495f244d31888ebf7ba7de9218e25203684 +size 3424736320