commit 1693c731b4cc29945ac6810895a383c1c66d4b6a Author: ModelHub XC Date: Sun May 10 07:46:22 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d89a84c --- /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 +deepseek-r1-distill-qwen-1-5b-kto.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-r1-distill-qwen-1-5b-kto.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..17deb1d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: abaryan/deepseek-r1-distill-qwen-1-5b-kto +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- kto +--- +## About + + + + + + +static quants of https://huggingface.co/abaryan/deepseek-r1-distill-qwen-1-5b-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/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/deepseek-r1-distill-qwen-1-5b-kto-GGUF/resolve/main/deepseek-r1-distill-qwen-1-5b-kto.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. + + diff --git a/deepseek-r1-distill-qwen-1-5b-kto.IQ4_XS.gguf b/deepseek-r1-distill-qwen-1-5b-kto.IQ4_XS.gguf new file mode 100644 index 0000000..d89d4fa --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99147b3c9094d32e64c7e40915d2850ada29752e1a8093986facf2f4de9a888e +size 1026163136 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q2_K.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q2_K.gguf new file mode 100644 index 0000000..981d1c1 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba670c2179c7920768d4263a2c8034972dc6ead4e08b1403642e336f6ad2c46 +size 752881088 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_L.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_L.gguf new file mode 100644 index 0000000..0b24a93 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77747c6327e1d4d623ae2bdada9c2e72192d3c0581de68c97c94ceb787c808a +size 980441024 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_M.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_M.gguf new file mode 100644 index 0000000..d7ced72 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b587722104d1214170301220baff592952e416fdf4607edea039cc67eebe6d1 +size 924456896 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_S.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_S.gguf new file mode 100644 index 0000000..485d358 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b3c718ec9223bd0576a04a4a37867faf8eed2277bf18211e6c6d1e1e575e19 +size 861222848 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_M.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_M.gguf new file mode 100644 index 0000000..9c38604 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dae6e4cd709baeeb717ff6059f068dbe4ae82fae39535908c209159578162ac +size 1117321664 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_S.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_S.gguf new file mode 100644 index 0000000..93e95fb --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c86a1a20983fa0bcdd35d0015a020919b95795b96823b875ee9dd67ac548ed7c +size 1071585728 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_M.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_M.gguf new file mode 100644 index 0000000..f46cf3f --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c241c38cf88a12124300283cec3f26356a1594d3bd7651186ff61fee6d3f31af +size 1285495232 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_S.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_S.gguf new file mode 100644 index 0000000..4ccc37a --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02aed9662f8e8d611ca39cb50576253a21679d9c8996cc51af413ec577cea22 +size 1259174336 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q6_K.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q6_K.gguf new file mode 100644 index 0000000..8577a1b --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f4b936b9528907d65d8def7f3b5b6bbba9752c44a014578a0ef2808c859cdb +size 1464179648 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.Q8_0.gguf b/deepseek-r1-distill-qwen-1-5b-kto.Q8_0.gguf new file mode 100644 index 0000000..f4f4894 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6be2630ecc1aea2df03201efaa0d15c8b39da214839baf8ba5498a323643e77 +size 1894533056 diff --git a/deepseek-r1-distill-qwen-1-5b-kto.f16.gguf b/deepseek-r1-distill-qwen-1-5b-kto.f16.gguf new file mode 100644 index 0000000..6717e25 --- /dev/null +++ b/deepseek-r1-distill-qwen-1-5b-kto.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7575e7d8d65df2d65c8c055bc9b710e9e60fe5f94456e3d846ac81eddd9b45bc +size 3560417216