commit 418c3c6176011eecf0ddf6f406a74aa45febd4b0 Author: ModelHub XC Date: Tue May 26 06:34:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/smollm-wizard-vicuna-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a436c6 --- /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 +smollm-wizard-vicuna.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +smollm-wizard-vicuna.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b20a7d7 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: marcuscedricridia/smollm-wizard-vicuna +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/marcuscedricridia/smollm-wizard-vicuna + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#smollm-wizard-vicuna-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/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/smollm-wizard-vicuna-GGUF/resolve/main/smollm-wizard-vicuna.f16.gguf) | f16 | 0.4 | 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/smollm-wizard-vicuna.IQ4_XS.gguf b/smollm-wizard-vicuna.IQ4_XS.gguf new file mode 100644 index 0000000..97aaa1c --- /dev/null +++ b/smollm-wizard-vicuna.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b472c23030380cb4c6e079cb425a217ed1b504037c0db5ab88d76029481aea +size 91313056 diff --git a/smollm-wizard-vicuna.Q2_K.gguf b/smollm-wizard-vicuna.Q2_K.gguf new file mode 100644 index 0000000..651a3fb --- /dev/null +++ b/smollm-wizard-vicuna.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be01e69d40f15bbbb74b03eb1097abfbd99a3a95d6f67190666120e60f1ad053 +size 88202656 diff --git a/smollm-wizard-vicuna.Q3_K_L.gguf b/smollm-wizard-vicuna.Q3_K_L.gguf new file mode 100644 index 0000000..a883295 --- /dev/null +++ b/smollm-wizard-vicuna.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10886a5503f599df4b5677987d747bbe5eb2a5af75503460e361b58f1ce69070 +size 97533856 diff --git a/smollm-wizard-vicuna.Q3_K_M.gguf b/smollm-wizard-vicuna.Q3_K_M.gguf new file mode 100644 index 0000000..606fc78 --- /dev/null +++ b/smollm-wizard-vicuna.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7f4d3444a29837991b794c71fc72b157833b17bbc5104aa57dd6867f8d8156 +size 93511072 diff --git a/smollm-wizard-vicuna.Q3_K_S.gguf b/smollm-wizard-vicuna.Q3_K_S.gguf new file mode 100644 index 0000000..7e074f2 --- /dev/null +++ b/smollm-wizard-vicuna.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f395ed66ece0710a238f262955101f1a344ca8371ca4b39109ae2f010116567 +size 88202656 diff --git a/smollm-wizard-vicuna.Q4_K_M.gguf b/smollm-wizard-vicuna.Q4_K_M.gguf new file mode 100644 index 0000000..1956027 --- /dev/null +++ b/smollm-wizard-vicuna.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d591dc92898587f25c565284ae463dbccf233809a3e568ed6c012a2b291005 +size 105455008 diff --git a/smollm-wizard-vicuna.Q4_K_S.gguf b/smollm-wizard-vicuna.Q4_K_S.gguf new file mode 100644 index 0000000..0b69b7f --- /dev/null +++ b/smollm-wizard-vicuna.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a70783a6040bdfbe8ab92f47d438cc242007a137ad649fc68cce3180697cd5b +size 102040480 diff --git a/smollm-wizard-vicuna.Q5_K_M.gguf b/smollm-wizard-vicuna.Q5_K_M.gguf new file mode 100644 index 0000000..716dadf --- /dev/null +++ b/smollm-wizard-vicuna.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f3ad24ae86f10fa7efb2d1784d11414404985809f0b08d8944ca14ec44f16f +size 112104352 diff --git a/smollm-wizard-vicuna.Q5_K_S.gguf b/smollm-wizard-vicuna.Q5_K_S.gguf new file mode 100644 index 0000000..3cd32e2 --- /dev/null +++ b/smollm-wizard-vicuna.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc8cdd6388ae683eedf1646d1508a66183d94b80f3a5f0b08bb7d29a6373ea2 +size 109975456 diff --git a/smollm-wizard-vicuna.Q6_K.gguf b/smollm-wizard-vicuna.Q6_K.gguf new file mode 100644 index 0000000..f9b1934 --- /dev/null +++ b/smollm-wizard-vicuna.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8576f896b36a61c54129a79b1682896a2b3916c028b0c00843fb87437c0ca88c +size 138383776 diff --git a/smollm-wizard-vicuna.Q8_0.gguf b/smollm-wizard-vicuna.Q8_0.gguf new file mode 100644 index 0000000..343c538 --- /dev/null +++ b/smollm-wizard-vicuna.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e5c3bc64d5be2dc91cf1e6b16f23e85ab671c1a2d5f5ca8e69abe80be60927 +size 144811936 diff --git a/smollm-wizard-vicuna.f16.gguf b/smollm-wizard-vicuna.f16.gguf new file mode 100644 index 0000000..ed04cc2 --- /dev/null +++ b/smollm-wizard-vicuna.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb5b6b409b811f322c398be283e966263f9ad27a2bc4ff91747eb47163d4b8c +size 270886816