commit 319d05e9c371060093365dbc4e6b80da627496d9 Author: ModelHub XC Date: Wed May 20 18:27:17 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-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..142c0dd --- /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-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.IQ4_XS.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..7c82822 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39b9712a40a5ee224e4562b98110c4daf39554589ca67fcd17503c265aa5f11 +size 4250297152 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q2_K.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q2_K.gguf new file mode 100644 index 0000000..c84edbe --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93210a3c1d01b07d6cb0fdc3899b05aa6548896b2e45dab7cf07d6d491097358 +size 3015938880 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_L.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..499ea7d --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60cfaa1827d76f176f28e8ae96302bd5a1c7d50b2180794627c146d81a085664 +size 4088458048 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_M.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..ea0594b --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8523b69a1ff57937feea18f0989d8e806454cf7469885b19c53389d2e20704dd +size 3808389952 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_S.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..e31525f --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e69c23333a07e765fea602ba9fbce1e0224cc673afa31259dc3ce3e8a00016d +size 3492367168 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_M.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..a0a711b --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d743213e08e4a20e33002dbde11b71065cefc912092ccc657a68d0f216f19ac +size 4683072320 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_S.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..95c2ce3 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b8765887d4154993e61d26cf1f46d2d060cde2f8c1ae500db92db9665b53b8 +size 4457767744 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_M.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..f8ab6c2 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ef4785a1a5c31ed392dd98672371f17e42cb7078e5d7e83add0eb12eb8f5c5 +size 5444830016 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_S.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..ac770bf --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01fec5618e6cc00a7fc414937011a829bf5162e9e055d33b05a32b8d4a6231d +size 5315175232 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q6_K.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q6_K.gguf new file mode 100644 index 0000000..13978f5 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4ba2b387a507ea5bf4bb3b129252d3ccc9db4031277d5240be9c4a80376ea4b +size 6254197568 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q8_0.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q8_0.gguf new file mode 100644 index 0000000..32d7039 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe542d153c40280d70e0504ea12269b4ba1ffa6b2f9e8882c89721643249d5f3 +size 8098523968 diff --git a/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.f16.gguf b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.f16.gguf new file mode 100644 index 0000000..6158343 --- /dev/null +++ b/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3016c05d31af97efea41a14e9de8f85c0c66369c949e4d869017aebddc608d85 +size 15237851968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..83d7be8 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- orpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO + + + +***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-ORPO-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-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.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-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.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-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.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-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO-GGUF/resolve/main/Qwen2.5-7B-sft-SPIN-Qwen2.5-72B-Instruct-ORPO.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. + +