commit 00b33a997b490c1ffbb7dc6c2a8e24a6306a615f Author: ModelHub XC Date: Sun Apr 12 04:55:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolLM2-70M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40f7ad2 --- /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 +SmolLM2-70M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-70M.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..509b9e1 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: codelion/SmolLM2-70M +datasets: +- codelion/sutra-10B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- pretraining +- educational +- pedagogical +- sutra +- smollm2 +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/codelion/SmolLM2-70M + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SmolLM2-70M-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/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q2_K.gguf) | Q2_K | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q3_K_S.gguf) | Q3_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM2-70M-GGUF/resolve/main/SmolLM2-70M.f16.gguf) | f16 | 0.2 | 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/SmolLM2-70M.IQ4_XS.gguf b/SmolLM2-70M.IQ4_XS.gguf new file mode 100644 index 0000000..154eb4f --- /dev/null +++ b/SmolLM2-70M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be7165d07f72c401f7d8360203a2b025ca3807f3b1831b4d5f03eb8de0545a4 +size 50105280 diff --git a/SmolLM2-70M.Q2_K.gguf b/SmolLM2-70M.Q2_K.gguf new file mode 100644 index 0000000..345ee7c --- /dev/null +++ b/SmolLM2-70M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac300aadb4929115d679281d1ca48eda319b7932eeeefef85beff0b081caf884 +size 48581568 diff --git a/SmolLM2-70M.Q3_K_L.gguf b/SmolLM2-70M.Q3_K_L.gguf new file mode 100644 index 0000000..58c03d0 --- /dev/null +++ b/SmolLM2-70M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fbfd316984d40e32ef1eab7eb08253c65bcc215ccbc0dba05830c80b54b742 +size 53005248 diff --git a/SmolLM2-70M.Q3_K_M.gguf b/SmolLM2-70M.Q3_K_M.gguf new file mode 100644 index 0000000..48c9627 --- /dev/null +++ b/SmolLM2-70M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4329fb9af3c0407b55541b3753343cafa30278a887d1533c7b594824ed8f6ab9 +size 51143616 diff --git a/SmolLM2-70M.Q3_K_S.gguf b/SmolLM2-70M.Q3_K_S.gguf new file mode 100644 index 0000000..ad6e054 --- /dev/null +++ b/SmolLM2-70M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7859843c4bd759c1a221d51103200f1f97a53b5438a71aa44026128f647b8d06 +size 48581568 diff --git a/SmolLM2-70M.Q4_K_M.gguf b/SmolLM2-70M.Q4_K_M.gguf new file mode 100644 index 0000000..8f20554 --- /dev/null +++ b/SmolLM2-70M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b28faabda39bc55ff2f036d58fd5928b7472b7a806497944078ae0f1802c1c +size 56888256 diff --git a/SmolLM2-70M.Q4_K_S.gguf b/SmolLM2-70M.Q4_K_S.gguf new file mode 100644 index 0000000..bb57d0f --- /dev/null +++ b/SmolLM2-70M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f62e2a1df170e2097c0d221c3b3d063b93fccf0844a9c3e143355d723f09bb2a +size 55180224 diff --git a/SmolLM2-70M.Q5_K_M.gguf b/SmolLM2-70M.Q5_K_M.gguf new file mode 100644 index 0000000..28da537 --- /dev/null +++ b/SmolLM2-70M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ab0020c1cc6d3bdec092e509e00c84d3ced2953b359767114ee5c3ce71ece4 +size 59984832 diff --git a/SmolLM2-70M.Q5_K_S.gguf b/SmolLM2-70M.Q5_K_S.gguf new file mode 100644 index 0000000..7a52fad --- /dev/null +++ b/SmolLM2-70M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb39221a61ed1e5f991cbf7a446d871e6379df0b5b50d727eadcc12b56bdab15 +size 58903488 diff --git a/SmolLM2-70M.Q6_K.gguf b/SmolLM2-70M.Q6_K.gguf new file mode 100644 index 0000000..ca10314 --- /dev/null +++ b/SmolLM2-70M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17fa2f5cc2d077404b258af50feeb7a2bbd8d2cf1e82beb7875a697e1c459208 +size 72371136 diff --git a/SmolLM2-70M.Q8_0.gguf b/SmolLM2-70M.Q8_0.gguf new file mode 100644 index 0000000..fe5a41e --- /dev/null +++ b/SmolLM2-70M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374e3611692ed859d68c7dc38a0124688efceecc23162c7bc66f08280cd22d4e +size 75418560 diff --git a/SmolLM2-70M.f16.gguf b/SmolLM2-70M.f16.gguf new file mode 100644 index 0000000..22f2dc3 --- /dev/null +++ b/SmolLM2-70M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc70cbb580e0aad635481664743bfb8fcb41f4fe5f6c98ddd3650c332a1ab68 +size 140299200