commit 315ca29aa0b9c50590bbaf0dd8dcdc84a63c5bd9 Author: ModelHub XC Date: Sun May 10 02:33:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolLM2-1.7B-16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9635937 --- /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 +SmolLM2-1.7B-16k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-16k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f1856f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ali-elganzory/SmolLM2-1.7B-16k +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ali-elganzory/SmolLM2-1.7B-16k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmolLM2-1.7B-16k-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/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-1.7B-16k-GGUF/resolve/main/SmolLM2-1.7B-16k.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-16k.IQ4_XS.gguf b/SmolLM2-1.7B-16k.IQ4_XS.gguf new file mode 100644 index 0000000..4f9545c --- /dev/null +++ b/SmolLM2-1.7B-16k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d1559d005a5471cf923530f5d64cc3973c1ec5eb112215da857a57060a046e +size 948371616 diff --git a/SmolLM2-1.7B-16k.Q2_K.gguf b/SmolLM2-1.7B-16k.Q2_K.gguf new file mode 100644 index 0000000..f254efb --- /dev/null +++ b/SmolLM2-1.7B-16k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80a3f5f4cd6f93f4d3ab6f24becc153c1015a904e63def007b467b4fc867bed +size 674693280 diff --git a/SmolLM2-1.7B-16k.Q3_K_L.gguf b/SmolLM2-1.7B-16k.Q3_K_L.gguf new file mode 100644 index 0000000..3952145 --- /dev/null +++ b/SmolLM2-1.7B-16k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f7df77861094f37abea09e99f461f25c120695ac77f64106eedae951c0377b +size 932642976 diff --git a/SmolLM2-1.7B-16k.Q3_K_M.gguf b/SmolLM2-1.7B-16k.Q3_K_M.gguf new file mode 100644 index 0000000..beda65c --- /dev/null +++ b/SmolLM2-1.7B-16k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec916d4a9793055f97f7c05379e0c01b1538e78095dbf704aff42c2c90353e8 +size 860291232 diff --git a/SmolLM2-1.7B-16k.Q3_K_S.gguf b/SmolLM2-1.7B-16k.Q3_K_S.gguf new file mode 100644 index 0000000..3d5e225 --- /dev/null +++ b/SmolLM2-1.7B-16k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e51ca8c295ebce2159c5fc9e1d7f59810b1b4b3201b846e16d932a1275b59c5 +size 776929440 diff --git a/SmolLM2-1.7B-16k.Q4_K_M.gguf b/SmolLM2-1.7B-16k.Q4_K_M.gguf new file mode 100644 index 0000000..b4c7d75 --- /dev/null +++ b/SmolLM2-1.7B-16k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a045f3d660f670bf16924e5f99504f138a3018f026681dc747e4991762d271e0 +size 1055719584 diff --git a/SmolLM2-1.7B-16k.Q4_K_S.gguf b/SmolLM2-1.7B-16k.Q4_K_S.gguf new file mode 100644 index 0000000..7243f1e --- /dev/null +++ b/SmolLM2-1.7B-16k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f95193793e798f388641371c4f8dbaf6558121b001f426a9b15d91d4201e52 +size 999227552 diff --git a/SmolLM2-1.7B-16k.Q5_K_M.gguf b/SmolLM2-1.7B-16k.Q5_K_M.gguf new file mode 100644 index 0000000..96da3b3 --- /dev/null +++ b/SmolLM2-1.7B-16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db0d2edbb3b3c133ccfb52a2d855aff8e4cf550f520ffe1d6f4b36d44770660 +size 1225588896 diff --git a/SmolLM2-1.7B-16k.Q5_K_S.gguf b/SmolLM2-1.7B-16k.Q5_K_S.gguf new file mode 100644 index 0000000..8dc54d2 --- /dev/null +++ b/SmolLM2-1.7B-16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870d4492b81e4260f99b51bd76f77bf0bef99f8cca7033745871bdb413cc5912 +size 1192165536 diff --git a/SmolLM2-1.7B-16k.Q6_K.gguf b/SmolLM2-1.7B-16k.Q6_K.gguf new file mode 100644 index 0000000..dff775f --- /dev/null +++ b/SmolLM2-1.7B-16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5eeaae9ae0697221d7504ef14b53b2cf936cf8bfa24f80bd89953226a67246 +size 1406075040 diff --git a/SmolLM2-1.7B-16k.Q8_0.gguf b/SmolLM2-1.7B-16k.Q8_0.gguf new file mode 100644 index 0000000..d3df47b --- /dev/null +++ b/SmolLM2-1.7B-16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e6664e1b861eee1a5640ddb63f747a6457acc408b33a4a1493dbffe3c7bd2e +size 1820556448 diff --git a/SmolLM2-1.7B-16k.f16.gguf b/SmolLM2-1.7B-16k.f16.gguf new file mode 100644 index 0000000..a5eacef --- /dev/null +++ b/SmolLM2-1.7B-16k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae390e7eae1d527bcb47f6b586219d9d41bbb0596c11686377591a7b4ad1d47 +size 3425000608