commit 7af15c61c8a1426e38bfb600396e388a55f2fe7d Author: ModelHub XC Date: Mon Jun 15 09:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quark-135m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45c07a5 --- /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 +Quark-135m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Quark-135m.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quark-135m.IQ4_XS.gguf b/Quark-135m.IQ4_XS.gguf new file mode 100644 index 0000000..7237267 --- /dev/null +++ b/Quark-135m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8678c74983b2ef69a31fefe8d6f5d80f608c5afb78a8439efc99af2c5760e38 +size 91503168 diff --git a/Quark-135m.Q2_K.gguf b/Quark-135m.Q2_K.gguf new file mode 100644 index 0000000..3f5eb56 --- /dev/null +++ b/Quark-135m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02402ede35cf1e8c81ed9441f2bbfa93bff8bf586ff2ff5c4db781f9a5bdcaf3 +size 88392768 diff --git a/Quark-135m.Q3_K_L.gguf b/Quark-135m.Q3_K_L.gguf new file mode 100644 index 0000000..9b441af --- /dev/null +++ b/Quark-135m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae2860c7a838a38d16a2f1fde347a9a843015c98bc9d811836621e176fc619c +size 97723968 diff --git a/Quark-135m.Q3_K_M.gguf b/Quark-135m.Q3_K_M.gguf new file mode 100644 index 0000000..387e115 --- /dev/null +++ b/Quark-135m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0eb5853d7ce28e796018abb60571e131811712821266353c21260ba4acbe6b2 +size 93701184 diff --git a/Quark-135m.Q3_K_S.gguf b/Quark-135m.Q3_K_S.gguf new file mode 100644 index 0000000..5e89bca --- /dev/null +++ b/Quark-135m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c19aaab6c107168f71585bc9f2a7398e37d7f191ed527294c78351d1d7a528 +size 88392768 diff --git a/Quark-135m.Q4_K_M.gguf b/Quark-135m.Q4_K_M.gguf new file mode 100644 index 0000000..2f56f91 --- /dev/null +++ b/Quark-135m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f7e7b8e1d4bc0f7fe6e723be0cdc7e51649c401219f3f95a9725cb86b2f97c1 +size 105645120 diff --git a/Quark-135m.Q4_K_S.gguf b/Quark-135m.Q4_K_S.gguf new file mode 100644 index 0000000..6472b10 --- /dev/null +++ b/Quark-135m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379cae5d0f566dd747d9318c634d574a0373884c98a9f882e5988adb8e9a5487 +size 102230592 diff --git a/Quark-135m.Q5_K_M.gguf b/Quark-135m.Q5_K_M.gguf new file mode 100644 index 0000000..ef91c51 --- /dev/null +++ b/Quark-135m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bccd96ace6c13575ee46be7bbc8b62547c69b5cca038bd29c236c819808e95a +size 112294464 diff --git a/Quark-135m.Q5_K_S.gguf b/Quark-135m.Q5_K_S.gguf new file mode 100644 index 0000000..3c174c5 --- /dev/null +++ b/Quark-135m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d00dfd8ba6e813e11aa15b1c00f58ad3f8431da7b3af98250d425b1841cf5e +size 110165568 diff --git a/Quark-135m.Q6_K.gguf b/Quark-135m.Q6_K.gguf new file mode 100644 index 0000000..d966aaa --- /dev/null +++ b/Quark-135m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6708d34284912be4cc0bf6e1229626775cb29210fb08219043d3ca173affdf02 +size 138573888 diff --git a/Quark-135m.Q8_0.gguf b/Quark-135m.Q8_0.gguf new file mode 100644 index 0000000..20c8913 --- /dev/null +++ b/Quark-135m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcdf2c7ff220e2f143c90c82381a81fb2dd3948760dee7c9e252d22bdd52a499 +size 145002048 diff --git a/Quark-135m.f16.gguf b/Quark-135m.f16.gguf new file mode 100644 index 0000000..c690c23 --- /dev/null +++ b/Quark-135m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f29f0f34bfda477f95eaa9a13df70b473af6ac9a6a89cbc0f5b82681019103bb +size 271076928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a5041c2 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: ThingAI/Quark-135m +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chat +- instruct +- small-model +- 135m +- quark +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ThingAI/Quark-135m + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Quark-135m-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/Quark-135m-GGUF/resolve/main/Quark-135m.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Quark-135m-GGUF/resolve/main/Quark-135m.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. + +