commit 6c69991089c3eba7c550d3a2007b686ff530470f Author: ModelHub XC Date: Thu Jul 9 15:44:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DOT-4K-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a0cd0c0 --- /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 +DOT-4K-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DOT-4K-1.5B.IQ4_XS.gguf b/DOT-4K-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..7a01ac1 --- /dev/null +++ b/DOT-4K-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee92aa03e7e3a652ac37bd5a5508e2db3eebaf58fbe88a0107646c3326b1605 +size 1026162528 diff --git a/DOT-4K-1.5B.Q2_K.gguf b/DOT-4K-1.5B.Q2_K.gguf new file mode 100644 index 0000000..837d2be --- /dev/null +++ b/DOT-4K-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72ad42aa76f19656bd3272a0cda3345ad02dcd49e0ada948ab328993a8e16ca +size 752880480 diff --git a/DOT-4K-1.5B.Q3_K_L.gguf b/DOT-4K-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..836b7cf --- /dev/null +++ b/DOT-4K-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1c6d11fc16ed525e3e8364ae14ca878a9f36c91278fa13c8c5aa099f1e5da5 +size 980440416 diff --git a/DOT-4K-1.5B.Q3_K_M.gguf b/DOT-4K-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..b05130e --- /dev/null +++ b/DOT-4K-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e791028edc1e761e82ea8958b73b61a18602a40fe5402f656dc0467923a2ac +size 924456288 diff --git a/DOT-4K-1.5B.Q3_K_S.gguf b/DOT-4K-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..74a138c --- /dev/null +++ b/DOT-4K-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d449e8c180c9ed02ad9eabef029ab48d02a6044293104b85a63fa5fb09b829 +size 861222240 diff --git a/DOT-4K-1.5B.Q4_K_M.gguf b/DOT-4K-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..2034996 --- /dev/null +++ b/DOT-4K-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d31604d56e239dfcbe309464caa7a37e5c172b641254102f3f1786b34e8fa265 +size 1117321056 diff --git a/DOT-4K-1.5B.Q4_K_S.gguf b/DOT-4K-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..29bff36 --- /dev/null +++ b/DOT-4K-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac93243ace6e89ef00a9322791f8f2b42eec0190eaf2ef5b8570ce6ae2077a8 +size 1071585120 diff --git a/DOT-4K-1.5B.Q5_K_M.gguf b/DOT-4K-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..cd1d9c4 --- /dev/null +++ b/DOT-4K-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd279a4de11381959e5fabf98c88d4efa500601920e1eb817e8a2d1305b7a96c +size 1285494624 diff --git a/DOT-4K-1.5B.Q5_K_S.gguf b/DOT-4K-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..0a0f462 --- /dev/null +++ b/DOT-4K-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6eda529fd0671f339cbf4fc9c01cf322fe7ae8632536d055bfb9d0004217ef +size 1259173728 diff --git a/DOT-4K-1.5B.Q6_K.gguf b/DOT-4K-1.5B.Q6_K.gguf new file mode 100644 index 0000000..1bc02c5 --- /dev/null +++ b/DOT-4K-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d96a1b3072b830e70c08850910f1c300a07141d17190b10010db45fcefc3e2 +size 1464179040 diff --git a/DOT-4K-1.5B.Q8_0.gguf b/DOT-4K-1.5B.Q8_0.gguf new file mode 100644 index 0000000..aca9dd0 --- /dev/null +++ b/DOT-4K-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd7e5b70d49faadddcb4ff195edffa3ed65749cb2cd742102f8f95688bf848e +size 1894532448 diff --git a/DOT-4K-1.5B.f16.gguf b/DOT-4K-1.5B.f16.gguf new file mode 100644 index 0000000..87925b0 --- /dev/null +++ b/DOT-4K-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5752fe888ffacd6923cc3bc9fff001ef0dce6f10d4789c4d95eac093d618184 +size 3560416608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a71d50f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: U-rara/DOT-4K-1.5B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/U-rara/DOT-4K-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DOT-4K-1.5B-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/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-1.5B-GGUF/resolve/main/DOT-4K-1.5B.f16.gguf) | f16 | 3.7 | 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. + +