commit b41871d48ff5d416ced505e4fd6a70e537bf6402 Author: ModelHub XC Date: Sun Jun 14 23:26:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Chat-KTO-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b37c585 --- /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 +Chat-KTO-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Chat-KTO-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Chat-KTO-4B.IQ4_XS.gguf b/Chat-KTO-4B.IQ4_XS.gguf new file mode 100644 index 0000000..ad1dde8 --- /dev/null +++ b/Chat-KTO-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f7a46638babdbbad1fdfa4ba1582ca123172efdf7fe08c98323e40773c8df6 +size 2553240640 diff --git a/Chat-KTO-4B.Q2_K.gguf b/Chat-KTO-4B.Q2_K.gguf new file mode 100644 index 0000000..cdcb11d --- /dev/null +++ b/Chat-KTO-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d732333cd9e612799c23bb0dd38d7d258bae5221c79016fd8aac2ba735e57f9 +size 1839737920 diff --git a/Chat-KTO-4B.Q3_K_L.gguf b/Chat-KTO-4B.Q3_K_L.gguf new file mode 100644 index 0000000..cfbb4fa --- /dev/null +++ b/Chat-KTO-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f3094c0e3719f81deabde32a97efe678a2a25d05963ba3c867582bf12794100 +size 2464859200 diff --git a/Chat-KTO-4B.Q3_K_M.gguf b/Chat-KTO-4B.Q3_K_M.gguf new file mode 100644 index 0000000..c30ab39 --- /dev/null +++ b/Chat-KTO-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c16e4bb96aed08fd2decfab35863af178737df872df5a7158917251f8479d5 +size 2296562752 diff --git a/Chat-KTO-4B.Q3_K_S.gguf b/Chat-KTO-4B.Q3_K_S.gguf new file mode 100644 index 0000000..e68df4f --- /dev/null +++ b/Chat-KTO-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbe8d02dcbd6fecedeae4d1bb2a024a05ee2ab16f7f5e2651cae9417f548092 +size 2101527616 diff --git a/Chat-KTO-4B.Q4_K_M.gguf b/Chat-KTO-4B.Q4_K_M.gguf new file mode 100644 index 0000000..c7bf9aa --- /dev/null +++ b/Chat-KTO-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cee413e850b50de39a5bc494a4dda5682a8893e4a37eef47040e528a531930f +size 2778283072 diff --git a/Chat-KTO-4B.Q4_K_S.gguf b/Chat-KTO-4B.Q4_K_S.gguf new file mode 100644 index 0000000..b204a3c --- /dev/null +++ b/Chat-KTO-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbbaab0ffff7e551295df8c30d19eaee46a5bbf5cdebea24d0fd1fbc93f88393 +size 2664250432 diff --git a/Chat-KTO-4B.Q5_K_M.gguf b/Chat-KTO-4B.Q5_K_M.gguf new file mode 100644 index 0000000..bdab026 --- /dev/null +++ b/Chat-KTO-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecbf6518e95594bc59bce1148079555a9952c62e9c6f4d549e32f600300f439c +size 3230186560 diff --git a/Chat-KTO-4B.Q5_K_S.gguf b/Chat-KTO-4B.Q5_K_S.gguf new file mode 100644 index 0000000..a79dfc2 --- /dev/null +++ b/Chat-KTO-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4b885074131d8ad5c44b265359a287932db780e891a7cbb15e2e160794ec67 +size 3163339840 diff --git a/Chat-KTO-4B.Q6_K.gguf b/Chat-KTO-4B.Q6_K.gguf new file mode 100644 index 0000000..7e01c55 --- /dev/null +++ b/Chat-KTO-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5568ce5bbec37bd474e7173f6660e823aec9a2698dabba3cc396359a74eff693 +size 3710334016 diff --git a/Chat-KTO-4B.Q8_0.gguf b/Chat-KTO-4B.Q8_0.gguf new file mode 100644 index 0000000..5d9f7ad --- /dev/null +++ b/Chat-KTO-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3c709ad814b356ba59fd5af4b7cc878d9fecb614ea3dc244d1070dbaeaa549 +size 4803216448 diff --git a/Chat-KTO-4B.f16.gguf b/Chat-KTO-4B.f16.gguf new file mode 100644 index 0000000..8b75a3a --- /dev/null +++ b/Chat-KTO-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa41806de2a69c50e391bb4660f1b16cd54b95c9e1158711058c764a0b6a800c +size 9033729088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c2be11a --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Edens-Gate/Chat-KTO-4B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Edens-Gate/Chat-KTO-4B + + +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/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.IQ4_XS.gguf) | IQ4_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q5_K_S.gguf) | Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q6_K.gguf) | Q6_K | 3.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Chat-KTO-4B-GGUF/resolve/main/Chat-KTO-4B.f16.gguf) | f16 | 9.1 | 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. + +