commit 980fb7146f92570a0522fa3640711295606e3ddb Author: ModelHub XC Date: Sat Jun 20 21:51:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DRT-o1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..681cbd7 --- /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 +DRT-o1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DRT-o1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DRT-o1-8B.IQ4_XS.gguf b/DRT-o1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..25072d3 --- /dev/null +++ b/DRT-o1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:055fd789b7dcdcb34b948cdd6c3fa448cab19b55349bd59f0593432b0460f867 +size 4484368192 diff --git a/DRT-o1-8B.Q2_K.gguf b/DRT-o1-8B.Q2_K.gguf new file mode 100644 index 0000000..131365a --- /dev/null +++ b/DRT-o1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0630dc3a10ed1448ace9eebe6d93471ad0eca1657ff32991d9bdfa72caf494d +size 3179136832 diff --git a/DRT-o1-8B.Q3_K_L.gguf b/DRT-o1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..96d96d2 --- /dev/null +++ b/DRT-o1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d011040989dd3c127f9e7f27420244b65ac13c6365f2a69b6f5f7a119f2da1a +size 4321961792 diff --git a/DRT-o1-8B.Q3_K_M.gguf b/DRT-o1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..ca1a06e --- /dev/null +++ b/DRT-o1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4066ad74d1d23248e0413998847d0383649e5357a7fada1a459c84aed3cb1c38 +size 4018923328 diff --git a/DRT-o1-8B.Q3_K_S.gguf b/DRT-o1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..d416694 --- /dev/null +++ b/DRT-o1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2fa8e0d01b0addfc6b8051eb79a2dee7a64ad37659fea9367615d6cd4a6eae +size 3664504640 diff --git a/DRT-o1-8B.Q4_K_M.gguf b/DRT-o1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a8dba35 --- /dev/null +++ b/DRT-o1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b2c231f2664126bd9a5fd15e485b4f3e48a72a27b1c5b104c3c33a9ddf27dd7 +size 4920739648 diff --git a/DRT-o1-8B.Q4_K_S.gguf b/DRT-o1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..c1b5b90 --- /dev/null +++ b/DRT-o1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c92f83b51c168d410e86eba0edccf1f82c374a7e1f22ce6289017958a32e44 +size 4692674368 diff --git a/DRT-o1-8B.Q5_K_M.gguf b/DRT-o1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..0d1be3b --- /dev/null +++ b/DRT-o1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ede9af1dbd2d861625e9f5f287801706fb242b19baefdab37e2920f2720b45ca +size 5732992832 diff --git a/DRT-o1-8B.Q5_K_S.gguf b/DRT-o1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..d85dcff --- /dev/null +++ b/DRT-o1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98856736fc0c2b5c34ecc0d67670d6ea61e03cc490684799050bcebf6a428293 +size 5599299392 diff --git a/DRT-o1-8B.Q6_K.gguf b/DRT-o1-8B.Q6_K.gguf new file mode 100644 index 0000000..b2cb63b --- /dev/null +++ b/DRT-o1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b21c396aaff2d902a863ff538bd12920e3a3be4588f6d91d2e8d01b8b20af3 +size 6596011840 diff --git a/DRT-o1-8B.Q8_0.gguf b/DRT-o1-8B.Q8_0.gguf new file mode 100644 index 0000000..0bdf02a --- /dev/null +++ b/DRT-o1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841d485c28bab948a4903b6e5da1e8997a1fc1840ea530cd04e63784575530c6 +size 8540776256 diff --git a/DRT-o1-8B.f16.gguf b/DRT-o1-8B.f16.gguf new file mode 100644 index 0000000..95b29c0 --- /dev/null +++ b/DRT-o1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe068f3cab20214f0a641d718912eecd7e793119719f4af7b1cef345b8af27ea +size 16068896576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..08c10a7 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Krystalan/DRT-8B +language: +- en +- zh +library_name: transformers +license: cc-by-nc-sa-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- machine tranlsation +- O1-like model +- Chat +--- +## About + + + + + + +static quants of https://huggingface.co/Krystalan/DRT-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DRT-o1-8B-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/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DRT-o1-8B-GGUF/resolve/main/DRT-o1-8B.f16.gguf) | f16 | 16.2 | 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. + +