commit ee9a23eb6809650bd032d86113cbca7f7720c2fc Author: ModelHub XC Date: Sat May 9 11:13:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..288726a --- /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-Qwen2.5-72B-Instruct-IPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.IQ4_XS.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.IQ4_XS.gguf new file mode 100644 index 0000000..dad0090 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee65eea072bfdea3ec8567d0c04076cc8e716d85d317ddb7910f16b4b8007349 +size 4250297152 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q2_K.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q2_K.gguf new file mode 100644 index 0000000..f468690 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d861c152aef57edebcc597d7a090b9416ac28f7e239888ba194a9fd3c81cc25 +size 3015938880 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_L.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_L.gguf new file mode 100644 index 0000000..db8335f --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7fcb5a743a2c5c79dc49316a5cf58a8821ab8d6531fab8fad3af01a2b800f7 +size 4088458048 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_M.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_M.gguf new file mode 100644 index 0000000..027efc8 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1a4a50f9f7ca632f894b875828d095e75c31b9a3db18f8873528bd215f1fd3 +size 3808389952 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_S.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_S.gguf new file mode 100644 index 0000000..f389912 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e75d852f530b243e86a99a9b35fd9fbe3455813c712798df956185bca6c4879 +size 3492367168 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_M.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_M.gguf new file mode 100644 index 0000000..52c1108 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c618612db31b56dbfba89ce2412c138de182f18a1e30795ca09b660d772ae1e +size 4683072320 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_S.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_S.gguf new file mode 100644 index 0000000..c99b9ca --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0498757ea199750fce58ef8d7c476626caa74dcacf8f2fb419ec4bef93a393 +size 4457767744 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_M.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_M.gguf new file mode 100644 index 0000000..ee6ed4d --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2338ef33d637eab5dabd833a7a1773f87b9543639f21b4beafc4e751780eb9e +size 5444830016 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_S.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_S.gguf new file mode 100644 index 0000000..5dcadac --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c56551b34c700d82d29ba8725ae1f8a76af4b46e9a00fb39343ece888a5d11 +size 5315175232 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q6_K.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q6_K.gguf new file mode 100644 index 0000000..211dc2b --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58685f651dbe911d9dc19f5001f0e2daa30c102fbe8171d467ee42d5dc444f78 +size 6254197568 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q8_0.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q8_0.gguf new file mode 100644 index 0000000..90f3b76 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab907f0857988c88b386b590372370b6d3d35dea54d477717525d908a5faeec3 +size 8098523968 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.f16.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.f16.gguf new file mode 100644 index 0000000..0bbfd70 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78623421a3e36dfecfd4bf98a5cad922d4e0b5846690dc79d045dbc504c6019 +size 15237851968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..db8908b --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-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-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-IPO.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. + +