commit a4830ba43bfe0e73e95423bb1e37ab8af8a8c158 Author: ModelHub XC Date: Wed May 20 16:24:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5ee365e --- /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 +Qwen2.5-7B-sft-spin-10k-KTO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-spin-10k-KTO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.IQ4_XS.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.IQ4_XS.gguf new file mode 100644 index 0000000..9880dab --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdf15c23a462bfda6766674c2656877488ee0b3e8202c8f2dd2084d69db2c61 +size 4250297088 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q2_K.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q2_K.gguf new file mode 100644 index 0000000..f476ced --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7b2cb97d445b19410ed3ea6d32576ee416e91a9b1dcfb449ee374abf22e996 +size 3015938816 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_L.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_L.gguf new file mode 100644 index 0000000..8b709d8 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:992c1f978787553aa135bd20b522408455c774face866388d67e19542c770e4e +size 4088457984 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_M.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_M.gguf new file mode 100644 index 0000000..5484172 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918a676c37c23af2a99b1908f6e846ad8116f871e80cfd664cbc02954b4990b9 +size 3808389888 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_S.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_S.gguf new file mode 100644 index 0000000..c003bbb --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d5d34ca4373a382167d5856f64a310a0b78dd4606e6ff642a2b9233dd2d7ad +size 3492367104 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_M.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_M.gguf new file mode 100644 index 0000000..ea183b4 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c761f8184d780c87af5adf0f3d5e5c8457065fe6818f6e5121ce09cc0b7976a2 +size 4683072256 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_S.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_S.gguf new file mode 100644 index 0000000..e218c39 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644de43a9042d1d8cb56774daa96362c7a61cff5105cbd826d0ddeb92a2d47c7 +size 4457767680 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_M.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_M.gguf new file mode 100644 index 0000000..1d2a809 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed0fa5b99038dfa265242fd8cb8d4376ad066ad40f5267a1405e9040631c430 +size 5444829952 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_S.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_S.gguf new file mode 100644 index 0000000..e6a1f7b --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7341e53f60afe75a2c506ef165834875e726f9b357c9da2b10737d55eaa30cee +size 5315175168 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q6_K.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q6_K.gguf new file mode 100644 index 0000000..de05316 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2264d4144ce2a5155849c3b874f3a8c79d5691428d348dc333080387bbe695e0 +size 6254197504 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.Q8_0.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.Q8_0.gguf new file mode 100644 index 0000000..faedfbf --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cc2bb83799792fc9d3e22b4bd89f67ed222e7e14217bee419e58a0f082fec9 +size 8098523904 diff --git a/Qwen2.5-7B-sft-spin-10k-KTO.f16.gguf b/Qwen2.5-7B-sft-spin-10k-KTO.f16.gguf new file mode 100644 index 0000000..3db4da6 --- /dev/null +++ b/Qwen2.5-7B-sft-spin-10k-KTO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d34f66d58d339c432ae7b1f2d9894cbc757facc1fcac6e2bda6fd1879829260 +size 15237851904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b2b4694 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-spin-10k-KTO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-spin-10k-KTO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- kto +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-sft-spin-10k-KTO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-sft-spin-10k-KTO-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/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-spin-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-spin-10k-KTO.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. + +