commit 29eab9bbc74d0ffbc3cb37cdaa3eb012c343c6aa Author: ModelHub XC Date: Thu Jul 9 15:58:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DOT-4K-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1e1c833 --- /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-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DOT-4K-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DOT-4K-7B.IQ4_XS.gguf b/DOT-4K-7B.IQ4_XS.gguf new file mode 100644 index 0000000..e20cc7c --- /dev/null +++ b/DOT-4K-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05749e6a97fca12d26a460e6c5291f6e5c7f9bd83fae15030820c83be90ed20b +size 4250298592 diff --git a/DOT-4K-7B.Q2_K.gguf b/DOT-4K-7B.Q2_K.gguf new file mode 100644 index 0000000..8a73b76 --- /dev/null +++ b/DOT-4K-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b78d6c69fc55d91a2310ec06ff4fbc999d5ef23ee21ea95acbbfde8c7b77821 +size 3015940320 diff --git a/DOT-4K-7B.Q3_K_L.gguf b/DOT-4K-7B.Q3_K_L.gguf new file mode 100644 index 0000000..25ba5b7 --- /dev/null +++ b/DOT-4K-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585cbb3d0a335d5ae12a9582e9ee6dfd408ff0def0557e01371152c0497d1624 +size 4088459488 diff --git a/DOT-4K-7B.Q3_K_M.gguf b/DOT-4K-7B.Q3_K_M.gguf new file mode 100644 index 0000000..6374ffc --- /dev/null +++ b/DOT-4K-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2e090a471ff0489ba9d643b10ca3914c7024ca03320f666259fdf76de5aaaa +size 3808391392 diff --git a/DOT-4K-7B.Q3_K_S.gguf b/DOT-4K-7B.Q3_K_S.gguf new file mode 100644 index 0000000..cf00264 --- /dev/null +++ b/DOT-4K-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7aa9606ce9887d6780ca409cea9f24e07fa9e9f3f288967652ebc8b3d31ce92 +size 3492368608 diff --git a/DOT-4K-7B.Q4_K_M.gguf b/DOT-4K-7B.Q4_K_M.gguf new file mode 100644 index 0000000..f466e48 --- /dev/null +++ b/DOT-4K-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4bdef1b7cbb202d77828d3a2fea09da6582d3508235251147177338dab0e6a +size 4683073760 diff --git a/DOT-4K-7B.Q4_K_S.gguf b/DOT-4K-7B.Q4_K_S.gguf new file mode 100644 index 0000000..ee8ad02 --- /dev/null +++ b/DOT-4K-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a44c854ddcf373be6c1632b977f562689e49347a6791961e0590fff6e8c1d3c +size 4457769184 diff --git a/DOT-4K-7B.Q5_K_M.gguf b/DOT-4K-7B.Q5_K_M.gguf new file mode 100644 index 0000000..77d5ee4 --- /dev/null +++ b/DOT-4K-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396a149db50b8332cce83bbf2b6012075154a3f61e65c0aca4e4d534e2f237df +size 5444831456 diff --git a/DOT-4K-7B.Q5_K_S.gguf b/DOT-4K-7B.Q5_K_S.gguf new file mode 100644 index 0000000..9d2011d --- /dev/null +++ b/DOT-4K-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da1b21f8f5e339247a2ddde45148b33022e46a8180e5bbc1c02272c2e38237ab +size 5315176672 diff --git a/DOT-4K-7B.Q6_K.gguf b/DOT-4K-7B.Q6_K.gguf new file mode 100644 index 0000000..af5348f --- /dev/null +++ b/DOT-4K-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d3c635afcdd1dc2945830a45d69ea755f1d26ff779f092f80a69bd87c12511 +size 6254199008 diff --git a/DOT-4K-7B.Q8_0.gguf b/DOT-4K-7B.Q8_0.gguf new file mode 100644 index 0000000..4dafd73 --- /dev/null +++ b/DOT-4K-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7558fa3e550d33a9720d464439722f4ff630bd996f8b1250f3a240e44866cc63 +size 8098525408 diff --git a/DOT-4K-7B.f16.gguf b/DOT-4K-7B.f16.gguf new file mode 100644 index 0000000..14e8c15 --- /dev/null +++ b/DOT-4K-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bacaf1464170ba672c41ac9fe68ee14f622f5974f7e59e2060c8bc1499ed8235 +size 15237853408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a396968 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: U-rara/DOT-4K-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/U-rara/DOT-4K-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DOT-4K-7B-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-7B-GGUF/resolve/main/DOT-4K-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DOT-4K-7B-GGUF/resolve/main/DOT-4K-7B.f16.gguf) | f16 | 15.3 | 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. + +