commit 395e52d6a60fbf9a362fccd832bd275fbd2b78e9 Author: ModelHub XC Date: Wed Jun 17 09:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GritLM-7B-KTO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75f2619 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +GritLM-7B-KTO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.f16.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GritLM-7B-KTO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GritLM-7B-KTO.IQ3_M.gguf b/GritLM-7B-KTO.IQ3_M.gguf new file mode 100644 index 0000000..0afc04d --- /dev/null +++ b/GritLM-7B-KTO.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2babfb1f2603f73f51a4829fc5d13cade64e1a1bccc2a62423eb54acd9942458 +size 3284892256 diff --git a/GritLM-7B-KTO.IQ3_S.gguf b/GritLM-7B-KTO.IQ3_S.gguf new file mode 100644 index 0000000..f952d0b --- /dev/null +++ b/GritLM-7B-KTO.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c3e9a68b577763a55ef1b9bebbc8da0918fae21701eb173d46bdc2a2cc11ac +size 3182393952 diff --git a/GritLM-7B-KTO.IQ3_XS.gguf b/GritLM-7B-KTO.IQ3_XS.gguf new file mode 100644 index 0000000..ad4274c --- /dev/null +++ b/GritLM-7B-KTO.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce7836de48945baa04f199a09b05ae47180388be2473e95d9a647805efb1980e +size 3018816096 diff --git a/GritLM-7B-KTO.IQ4_XS.gguf b/GritLM-7B-KTO.IQ4_XS.gguf new file mode 100644 index 0000000..e2f4cf8 --- /dev/null +++ b/GritLM-7B-KTO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec52d222e00c85646c60a7d7742af8f868cbfd803c90ac8f2ad32b4f2e7c4599 +size 3944389216 diff --git a/GritLM-7B-KTO.Q2_K.gguf b/GritLM-7B-KTO.Q2_K.gguf new file mode 100644 index 0000000..a85bf0c --- /dev/null +++ b/GritLM-7B-KTO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9f942e99270efb7361b769a884c1798ef6d3883a82cc00b64df03beddf5c3a +size 2719242848 diff --git a/GritLM-7B-KTO.Q3_K_L.gguf b/GritLM-7B-KTO.Q3_K_L.gguf new file mode 100644 index 0000000..fc3046b --- /dev/null +++ b/GritLM-7B-KTO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb57575dad9e007859a7ec59cb7fb5156fe015946cb6737052933e0d0f28ed4 +size 3822025312 diff --git a/GritLM-7B-KTO.Q3_K_M.gguf b/GritLM-7B-KTO.Q3_K_M.gguf new file mode 100644 index 0000000..208d5fe --- /dev/null +++ b/GritLM-7B-KTO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e1f387edf6b663ab3949ad3c1f291456eafb97c48ab4b063ccb617f70da100 +size 3518986848 diff --git a/GritLM-7B-KTO.Q3_K_S.gguf b/GritLM-7B-KTO.Q3_K_S.gguf new file mode 100644 index 0000000..de17743 --- /dev/null +++ b/GritLM-7B-KTO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb3f76bcd2ad078b39d3696ccf757e859a5c3029e94e7d04b80d1475bae80f9 +size 3164568160 diff --git a/GritLM-7B-KTO.Q4_K_M.gguf b/GritLM-7B-KTO.Q4_K_M.gguf new file mode 100644 index 0000000..32ec0d6 --- /dev/null +++ b/GritLM-7B-KTO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f64785d5d561d4bbcefe15301cd521fc8c629cbf57bd37cb9188f59df6a64ba +size 4368439904 diff --git a/GritLM-7B-KTO.Q4_K_S.gguf b/GritLM-7B-KTO.Q4_K_S.gguf new file mode 100644 index 0000000..6d81210 --- /dev/null +++ b/GritLM-7B-KTO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db081a46d8d3e8d12dfaeaa6187f86b7f75d1d4fb21d49b9232fc2b504329eb +size 4140374624 diff --git a/GritLM-7B-KTO.Q5_K_M.gguf b/GritLM-7B-KTO.Q5_K_M.gguf new file mode 100644 index 0000000..43c9995 --- /dev/null +++ b/GritLM-7B-KTO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5702300dffa93aa759e53bd9d55ad76eaf99b99912119a7add5205d37816be4c +size 5131410016 diff --git a/GritLM-7B-KTO.Q5_K_S.gguf b/GritLM-7B-KTO.Q5_K_S.gguf new file mode 100644 index 0000000..cfddfa9 --- /dev/null +++ b/GritLM-7B-KTO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbeb3dd9cfbd892843267f1abe1a1fc127038a5f5bebc32e66e1f7838f2d8ff +size 4997716576 diff --git a/GritLM-7B-KTO.Q6_K.gguf b/GritLM-7B-KTO.Q6_K.gguf new file mode 100644 index 0000000..4829af9 --- /dev/null +++ b/GritLM-7B-KTO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bb7fc0acc36e020c5bf0eeedf301e92972b62944aaf54c1d45466e6e444a61f +size 5942065760 diff --git a/GritLM-7B-KTO.Q8_0.gguf b/GritLM-7B-KTO.Q8_0.gguf new file mode 100644 index 0000000..3dd261f --- /dev/null +++ b/GritLM-7B-KTO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea07c95f603c33e22bf33d8b48424612d9db9d4a95e4f2b1e3e51ead698e730f +size 7695858272 diff --git a/GritLM-7B-KTO.f16.gguf b/GritLM-7B-KTO.f16.gguf new file mode 100644 index 0000000..8ac597f --- /dev/null +++ b/GritLM-7B-KTO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf03890669279f88411cd581645cf616161e700d5f7b7616bc8660b146b5029 +size 14484732512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..61b8d37 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: GritLM/GritLM-7B-KTO +datasets: +- GritLM/tulu2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/GritLM/GritLM-7B-KTO + + +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/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GritLM-7B-KTO-GGUF/resolve/main/GritLM-7B-KTO.f16.gguf) | f16 | 14.6 | 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. + +