commit 2d881277a5c1405ab89bc0f7ab2f5625508df9a1 Author: ModelHub XC Date: Tue Aug 11 21:37:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..84915ba --- /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 +GT-Qwen3-4B-Base-DAPO14k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GT-Qwen3-4B-Base-DAPO14k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GT-Qwen3-4B-Base-DAPO14k.IQ4_XS.gguf b/GT-Qwen3-4B-Base-DAPO14k.IQ4_XS.gguf new file mode 100644 index 0000000..6b477be --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca507701d1fa112add2271c4ad119ec9d9797748d9a52ad26e7f7880d81b53f9 +size 2492949280 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q2_K.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q2_K.gguf new file mode 100644 index 0000000..850b4f0 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73a14803a9a2a1d86976a70976114e0a0a8a92c6917a741f0b9a0b9bd01900c +size 1797125920 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q3_K_L.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q3_K_L.gguf new file mode 100644 index 0000000..3d0866e --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e30ac862cac0a4a46add0a7f866486a0b58316904c4df6a8ea726a42e1c82ee +size 2406915360 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q3_K_M.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q3_K_M.gguf new file mode 100644 index 0000000..1d36814 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b898a26bfde095e5a875aea0b60ba463d0d25341edd103af56eb51cb6e0d6749 +size 2242747680 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q3_K_S.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q3_K_S.gguf new file mode 100644 index 0000000..1525fe2 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63008769257f4653fd47e210698ce728528b9676da191a673022c24eb408d698 +size 2054126880 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q4_K_M.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q4_K_M.gguf new file mode 100644 index 0000000..37ea954 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422c6ff51aedda8a826615d4e8f7d7ba11d85b8116788f58f2de6a94b0fdccd9 +size 2716068640 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q4_K_S.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q4_K_S.gguf new file mode 100644 index 0000000..49328b7 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4b407a7724ef702af45ce46db3a3bca496ba59d8116c556e31f60f7a750943 +size 2602097440 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q5_K_M.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q5_K_M.gguf new file mode 100644 index 0000000..b71d209 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b9bf444df0ed195da838cdf85122fbd1cbd8906fe781e92a4655f0a6cbd4c6 +size 3156921120 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q5_K_S.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q5_K_S.gguf new file mode 100644 index 0000000..8caa940 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc72787f4b9050cee9baccee16068fe27f7b79a85cd5b597850b4d04d59cb88 +size 3091118880 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q6_K.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q6_K.gguf new file mode 100644 index 0000000..a352aa2 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712e71aedea9b78fcabf89ae0eafae56f413e9aa7e56ab97a2a8b977c69d0d7a +size 3625326880 diff --git a/GT-Qwen3-4B-Base-DAPO14k.Q8_0.gguf b/GT-Qwen3-4B-Base-DAPO14k.Q8_0.gguf new file mode 100644 index 0000000..5e79c00 --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d091322f7b4b574effb470c2204520434929bc69c275addb254857acb45f49 +size 4693671200 diff --git a/GT-Qwen3-4B-Base-DAPO14k.f16.gguf b/GT-Qwen3-4B-Base-DAPO14k.f16.gguf new file mode 100644 index 0000000..064802a --- /dev/null +++ b/GT-Qwen3-4B-Base-DAPO14k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a4a71e92ba8509b55e91f340aa70f765ca00dd94eb4337c8401d87a67ccfc9 +size 8829197600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d67b3c9 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: TMLR-Group-HF/GT-Qwen3-4B-Base-DAPO14k +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TMLR-Group-HF/GT-Qwen3-4B-Base-DAPO14k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GT-Qwen3-4B-Base-DAPO14k-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/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GT-Qwen3-4B-Base-DAPO14k-GGUF/resolve/main/GT-Qwen3-4B-Base-DAPO14k.f16.gguf) | f16 | 8.9 | 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. + +